INDEX

Explanations

verbs related to causing a change or making something unusable

oai_token-act-pair · gpt-3.5-turbo

occurrences 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 @ 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

!/

-0.67

 Eisen

-0.66

 Panama

-0.66

 Compton

-0.66

aterasu

-0.65

dayName

-0.65

Chel

-0.64

Cly

-0.64

uni

-0.64

 Greenberg

-0.63

POSITIVE LOGITS

 renders

0.99

ezvous

0.96

 render

0.94

 rendered

0.92

rendered

0.85

lete

0.77

 rendering

0.77

miah

0.74

render

0.74

utical

0.72

Activations Density 0.015%

verbs related to causing a change or making something unusable

occurrences of the word "render" and its variations

No Comments

No Known Activations