INDEX

Explanations

phrases or sentences where people are talking or being mentioned

oai_token-act-pair · gpt-3.5-turbo

topics related to social interactions and common conversations about people's perceptions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

etheless

-0.85

 overseen

-0.79

affer

-0.78

 ensured

-0.76

 bidder

-0.73

requisite

-0.73

rontal

-0.69

 complied

-0.68

sufficient

-0.68

 occupant

-0.68

POSITIVE LOGITS

 their

0.99

 themselves

0.97

 THEIR

0.95

their

0.93

 stuff

0.89

 crap

0.84

 diets

0.79

 theirs

0.78

 Their

0.78

 differently

0.77

Activations Density 0.475%

phrases or sentences where people are talking or being mentioned

topics related to social interactions and common conversations about people's perceptions

No Comments

No Known Activations