INDEX

Explanations

terms related to oppression and marginalized communities

oai_token-act-pair · gpt-3.5-turbo

terms related to oppression and marginalized groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tein

-0.82

cephal

-0.80

fleet

-0.77

WAYS

-0.75

uchin

-0.73

crypt

-0.72

intage

-0.70

abin

-0.69

sense

-0.67

ocular

-0.67

POSITIVE LOGITS

 oppression

0.88

 oppress

0.86

 oppressed

0.84

retched

0.79

ĸļ

0.79

 Struggle

0.73

 Nations

0.71

 Territories

0.70

 oppressive

0.69

 Palest

0.68

Activations Density 0.033%

terms related to oppression and marginalized communities

terms related to oppression and marginalized groups

No Comments

No Known Activations