INDEX

Explanations

words related to social issues and injustices

oai_token-act-pair · gpt-3.5-turbo

terms related to discrimination and social justice issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ramid

-0.73

FTWARE

-0.66

UTERS

-0.65

ultane

-0.65

è¦ļéĨĴ

-0.64

undred

-0.63

iem

-0.63

arta

-0.62

estones

-0.60

scill

-0.58

POSITIVE LOGITS

 perpetrators

1.00

 individuals

0.99

 them

0.94

 oneself

0.90

enance

0.88

him

0.87

 abusers

0.86

us

0.82

 anyone

0.82

 applicants

0.82

Activations Density 0.309%

words related to social issues and injustices

terms related to discrimination and social justice issues

No Comments

No Known Activations