INDEX

Explanations

references to movies or the film industry

oai_token-act-pair · gpt-3.5-turbo

references to the term "film" and its variations 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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

cffff

-0.77

BY

-0.65

esse

-0.65

bley

-0.65

itability

-0.63

rian

-0.63

abies

-0.63

ojure

-0.63

ilities

-0.63

ensional

-0.62

POSITIVE LOGITS

film

0.99

Film

0.98

ography

0.91

ographies

0.88

 adaptation

0.87

 studios

0.86

ctors

0.85

 films

0.85

goers

0.84

strip

0.84

Activations Density 0.045%

references to movies or the film industry

references to the term "film" and its variations in various contexts

No Comments

No Known Activations