INDEX

Explanations

information related to authors and creators of various content

oai_token-act-pair · gpt-3.5-turbo

elements related to authorship and credits in written works

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

 labour

-0.93

 organis

-0.79

 scrap

-0.76

 coerc

-0.74

 practise

-0.74

 abolished

-0.73

 migration

-0.72

 legisl

-0.72

 behavioural

-0.72

 administr

-0.72

POSITIVE LOGITS

Episode

1.10

Winner

0.99

Music

0.97

Guest

0.96

Scene

0.94

Released

0.93

pmwiki

0.93

Characters

0.91

Stream

0.90

Score

0.90

Activations Density 0.304%

information related to authors and creators of various content

elements related to authorship and credits in written works

No Comments

No Known Activations