INDEX

Explanations

mentions of the name "Rog" with varying degrees of similarity, possibly indicating a focus on detecting specific names or terms related to "Rog."

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Rog" and its variations in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 spaced

-0.74

 Tribal

-0.73

pora

-0.72

ãĥĩãĤ£

-0.67

ãĥ¯ãĥ³

-0.67

birth

-0.67

kHz

-0.66

 spores

-0.65

[]

-0.64

BIP

-0.62

POSITIVE LOGITS

ues

1.37

uel

1.24

uish

1.24

uers

1.08

ued

1.06

UE

1.03

atis

0.93

uing

0.91

adier

0.91

Rog

0.90

Activations Density 0.008%

mentions of the name "Rog" with varying degrees of similarity, possibly indicating a focus on detecting specific names or terms related to "Rog."

occurrences of the name "Rog" and its variations in various contexts

No Comments

No Known Activations