INDEX

Explanations

references to video footage

oai_token-act-pair · gpt-3.5-turbo

instances of "footage" and related terms 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 @ 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

inence

-0.73

 dement

-0.68

 Schwarz

-0.66

iott

-0.65

gently

-0.65

 conscientious

-0.63

patient

-0.62

mand

-0.60

 climates

-0.60

 boycot

-0.60

POSITIVE LOGITS

 footage

1.15

 clips

0.94

 filmed

0.89

 depicting

0.85

 clip

0.85

 CCTV

0.85

ography

0.83

 recorder

0.82

 Photographer

0.81

ographer

0.81

Activations Density 0.021%

references to video footage

instances of "footage" and related terms in various contexts

No Comments

No Known Activations