INDEX

Explanations

short sentences or phrases commonly used in software code or documentation

oai_token-act-pair · gpt-3.5-turbo

terms and references related to visual media and representations

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

merce

-0.75

acha

-0.73

ythm

-0.73

entimes

-0.72

 trusts

-0.72

iola

-0.68

 boycott

-0.68

awa

-0.68

akuya

-0.68

trust

-0.66

POSITIVE LOGITS

 excerpt

1.00

 Transcript

0.97

 pics

0.96

 screenshots

0.91

 photos

0.91

 images

0.90

 excerpts

0.89

 footage

0.87

 highlights

0.84

 details

0.83

Activations Density 0.649%

short sentences or phrases commonly used in software code or documentation

terms and references related to visual media and representations

No Comments

No Known Activations