INDEX

Explanations

names of famous actors and directors

oai_token-act-pair · gpt-3.5-turbo

names of actors and filmmakers in the context of film discussions

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

tnc

-0.71

 disadvantage

-0.69

 statist

-0.65

cknowled

-0.65

 counterproductive

-0.64

oard

-0.63

RESULTS

-0.63

Vim

-0.63

 futile

-0.63

 worthless

-0.62

POSITIVE LOGITS

enegger

1.09

 movies

0.95

 Studios

0.92

Film

0.91

 films

0.91

ovies

0.90

 actor

0.90

 actress

0.89

 Films

0.89

 Whedon

0.89

Activations Density 0.131%

names of famous actors and directors

names of actors and filmmakers in the context of film discussions

No Comments

No Known Activations