INDEX

Explanations

phrases related to personal possessions or identifiers, such as "My Music" or "My Space"

oai_token-act-pair · gpt-3.5-turbo

references to "My" 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

OPLE

-0.88

DERR

-0.77

inelli

-0.76

 Uriel

-0.76

itect

-0.76

INO

-0.74

ieri

-0.70

ERT

-0.68

Ø¯

-0.67

Ø³

-0.67

POSITIVE LOGITS

stery

1.28

riad

1.12

anmar

1.09

ths

1.04

self

0.98

stic

0.97

opia

0.91

ocard

0.88

chal

0.85

alg

0.83

Activations Density 0.053%

phrases related to personal possessions or identifiers, such as "My Music" or "My Space"

references to "My" in various contexts

No Comments

No Known Activations