INDEX

Explanations

phrases related to social justice and activism

oai_token-act-pair · gpt-3.5-turbo

references to social justice and activism

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

pload

-0.69

NTS

-0.68

lio

-0.66

xxxxxxxx

-0.65

 Starr

-0.64

nen

-0.61

zona

-0.61

 Himself

-0.60

paio

-0.60

 Dying

-0.60

POSITIVE LOGITS

economic

0.91

econom

0.83

apist

0.80

cultural

0.79

Economic

0.79

olitical

0.78

ocial

0.76

 norms

0.75

 spheres

0.73

geist

0.73

Activations Density 0.082%

phrases related to social justice and activism

references to social justice and activism

No Comments

No Known Activations