INDEX

Explanations

self-described or proclaimed identities or affiliations

oai_token-act-pair · gpt-3.5-turbo

phrases that refer to self-identifying labels or descriptors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Shoes

-0.81

perature

-0.81

isson

-0.74

utton

-0.73

vertisement

-0.72

inson

-0.71

von

-0.71

reau

-0.71

elight

-0.71

orrow

-0.71

POSITIVE LOGITS

 adherent

0.88

 believer

0.81

 caliphate

0.80

 atheist

0.76

 millennial

0.75

 badass

0.72

 bigot

0.70

 democratic

0.70

 socialist

0.70

 pacif

0.69

Activations Density 0.060%

self-described or proclaimed identities or affiliations

phrases that refer to self-identifying labels or descriptors

No Comments

No Known Activations