INDEX

Explanations

movies involving actors and their roles

oai_token-act-pair · gpt-3.5-turbo

action verbs specifically related to performance or acting roles in films and television

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

£ı

-0.84

wcs

-0.75

ensing

-0.72

ocating

-0.72

pora

-0.70

gencies

-0.70

plet

-0.70

à¼

-0.68

cling

-0.67

aching

-0.65

POSITIVE LOGITS

wright

1.31

rano

0.83

 roles

0.79

wr

0.78

ername

0.75

 havoc

0.72

 Sins

0.72

 Piano

0.71

 piano

0.70

plays

0.69

Activations Density 0.037%

movies involving actors and their roles

action verbs specifically related to performance or acting roles in films and television

No Comments

No Known Activations