INDEX

Explanations

mentions of identification in the text

oai_token-act-pair · gpt-3.5-turbo

terms related to identification and personal identification documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

orld

-0.87

uden

-0.86

imeo

-0.78

adj

-0.74

 bend

-0.71

ovie

-0.68

uss

-0.65

auld

-0.65

unin

-0.65

awar

-0.64

POSITIVE LOGITS

 identification

1.31

 Identification

1.09

eering

0.96

IDs

0.93

 identifiers

0.90

 identifier

0.85

 identifies

0.82

 credential

0.79

 credentials

0.77

 ident

0.77

Activations Density 0.008%

mentions of identification in the text

terms related to identification and personal identification documents

No Comments

No Known Activations