INDEX

Explanations

phrases related to discrimination and violence against vulnerable groups

oai_token-act-pair · gpt-3.5-turbo

references to discrimination and violence against various groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

soDeliveryDate

-1.07

ERN

-0.89

natureconservancy

-0.82

hower

-0.80

orah

-0.79

chell

-0.74

 Cosponsors

-0.71

}}}

-0.71

oppy

-0.70

psons

-0.69

POSITIVE LOGITS

soever

0.87

 civilians

0.85

 innocent

0.81

 humanity

0.78

 unborn

0.78

 barbar

0.76

 prostitutes

0.75

 harming

0.74

 women

0.74

 oppression

0.72

Activations Density 0.075%

phrases related to discrimination and violence against vulnerable groups

references to discrimination and violence against various groups

No Comments

No Known Activations