INDEX

Explanations

references to or mentions of movies

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "movie" 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 @ 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

ilities

-0.86

withstanding

-0.71

sembly

-0.71

ords

-0.70

 Haitian

-0.69

otics

-0.68

odox

-0.67

illin

-0.67

²¾

-0.67

anting

-0.66

POSITIVE LOGITS

 theater

1.08

goers

1.08

 theaters

1.05

 theatre

0.99

 movies

0.92

eers

0.91

going

0.88

 theat

0.88

 movie

0.87

 buffs

0.84

Activations Density 0.037%

references to or mentions of movies

occurrences of the word "movie" and its variations

No Comments

No Known Activations