INDEX

Explanations

references to movies

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "movie" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

-0.88

ords

-0.74

 Haitian

-0.72

odox

-0.70

sembly

-0.68

otics

-0.68

withstanding

-0.68

²¾

-0.67

anting

-0.66

cffff

-0.64

POSITIVE LOGITS

 theater

1.15

goers

1.11

 theaters

1.10

 theatre

1.06

 theat

0.96

 premie

0.93

going

0.91

 movies

0.91

eers

0.87

 movie

0.87

Activations Density 0.067%

references to movies

mentions of the word "movie" in various contexts

No Comments

No Known Activations