INDEX

Explanations

references to autographs

oai_token-act-pair · gpt-3.5-turbo

words related to autographs and signing memorabilia

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

bare

-0.76

 unexplained

-0.72

ahime

-0.69

ravis

-0.63

renheit

-0.61

 bare

-0.61

 nutshell

-0.60

 situational

-0.60

growth

-0.59

orney

-0.58

POSITIVE LOGITS

ographs

1.31

ograph

1.14

abilia

0.95

iques

0.94

ographed

0.86

 signings

0.86

*/(

0.81

ograp

0.80

ophone

0.78

 Juda

0.77

Activations Density 0.011%

references to autographs

words related to autographs and signing memorabilia

No Comments

No Known Activations