INDEX

Explanations

words or phrases related to social, economic, or political marginalization

oai_token-act-pair · gpt-3.5-turbo

terms related to marginalization and marginalization effects on various groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

uden

-0.71

ynthesis

-0.71

velt

-0.69

orld

-0.67

erver

-0.67

ILLE

-0.65

aternity

-0.64

boat

-0.62

 NETWORK

-0.62

IVERS

-0.62

POSITIVE LOGITS

ised

1.08

ization

1.01

ized

0.97

ities

0.85

aneously

0.85

iated

0.85

aneous

0.84

iary

0.83

izing

0.83

izes

0.82

Activations Density 0.025%

words or phrases related to social, economic, or political marginalization

terms related to marginalization and marginalization effects on various groups

No Comments

No Known Activations