INDEX

Explanations

movie-related terms

oai_token-act-pair · gpt-3.5-turbo

references to movies or the word "movie."

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

ilities

-0.79

raham

-0.71

sembly

-0.69

 Haitian

-0.68

urst

-0.68

withstanding

-0.68

otic

-0.68

cffff

-0.68

ords

-0.67

functional

-0.66

POSITIVE LOGITS

 theater

1.08

 theaters

1.07

goers

1.06

 movies

1.00

 theatre

0.98

 movie

0.96

 theat

0.89

eers

0.89

 premie

0.88

 Movies

0.88

Activations Density 0.039%

movie-related terms

references to movies or the word "movie."

No Comments

No Known Activations