INDEX

Explanations

punctuation marks, specifically commas

oai_token-act-pair · gpt-3.5-turbo

conjunctions, particularly ones that introduce contrast or additional information

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

chairs

-0.60

 suitcase

-0.59

Ike

-0.59

om

-0.54

AV

-0.54

 rehearsal

-0.53

XV

-0.53

bound

-0.53

cott

-0.53

 foreigner

-0.53

POSITIVE LOGITS

 nonetheless

0.87

âķĲâķĲ

0.81

 suffice

0.80

 beware

0.78

 acknow

0.77

 alas

0.77

ebus

0.76

 nevertheless

0.75

//[

0.74

 anecd

0.74

Activations Density 0.083%

punctuation marks, specifically commas

conjunctions, particularly ones that introduce contrast or additional information

No Comments

No Known Activations