INDEX

Explanations

abbreviations or terms related to technology or medical fields

oai_token-act-pair · gpt-3.5-turbo

occurrences of the abbreviation "SP" 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

taboola

-0.79

ãĥĥãĥĪ

-0.73

sbm

-0.73

 behold

-0.70

hower

-0.70

omorph

-0.69

ogen

-0.67

 subord

-0.67

omorphic

-0.66

ographed

-0.65

POSITIVE LOGITS

EED

1.37

ORT

1.16

ORTS

1.16

OIL

1.14

ONSORED

1.07

IR

0.99

HER

0.96

ECT

0.96

ENCE

0.94

OOL

0.94

Activations Density 0.013%

abbreviations or terms related to technology or medical fields

occurrences of the abbreviation "SP" in various contexts

No Comments

No Known Activations