INDEX

Explanations

information about movies

oai_token-act-pair · gpt-3.5-turbo

mentions of films or movies

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

cffff

-0.87

tnc

-0.77

²¾

-0.70

 tooth

-0.66

ĵĺ

-0.66

MpServer

-0.65

abies

-0.65

RESULTS

-0.64

ilities

-0.64

 exerc

-0.63

POSITIVE LOGITS

 adaptation

1.06

 theaters

0.97

ography

0.93

 studio

0.87

 studios

0.84

 theat

0.84

 sequels

0.84

 starring

0.83

 sequel

0.81

 premiered

0.81

Activations Density 0.046%

information about movies

mentions of films or movies

No Comments

No Known Activations