INDEX

Explanations

references to witnesses in legal or investigative contexts

oai_token-act-pair · gpt-3.5-turbo

words related to witnesses and testimony

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Saharan

-0.74

liga

-0.73

ofi

-0.73

ategory

-0.71

ooks

-0.70

osi

-0.68

 McMaster

-0.65

atism

-0.64

 Chop

-0.63

ATA

-0.62

POSITIVE LOGITS

 testimonies

1.01

Witness

0.97

 testimony

0.96

ewitness

0.96

 witnesses

0.95

 witness

0.95

 Witnesses

0.89

 testify

0.89

 testifying

0.85

 eyewitness

0.78

Activations Density 0.017%

references to witnesses in legal or investigative contexts

words related to witnesses and testimony

No Comments

No Known Activations