INDEX

Explanations

verbs related to causing a change or making something unusable

oai_token-act-pair · gpt-3.5-turbo

instances of the word "render" and its variations

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

dayName

-0.74

!/

-0.72

aterasu

-0.70

tar

-0.69

ramid

-0.68

estones

-0.68

RH

-0.67

ombs

-0.66

uni

-0.66

alg

-0.64

POSITIVE LOGITS

ezvous

0.98

 renders

0.97

 render

0.93

 rendered

0.87

rendered

0.80

 rendering

0.74

lete

0.73

 obsolete

0.69

ings

0.69

ables

0.69

Activations Density 0.023%

verbs related to causing a change or making something unusable

instances of the word "render" and its variations

No Comments

No Known Activations