INDEX

Explanations

instances of words related to legal documents or processes

oai_token-act-pair · gpt-3.5-turbo

instances of the word "writ" and related terms indicating legal documents or actions

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

bish

-0.91

Īè

-0.74

¶æ

-0.73

encies

-0.72

ences

-0.68

cloth

-0.64

ŀ

-0.64

ķ

-0.62

SHIP

-0.62

 DRAG

-0.61

POSITIVE LOGITS

 Remastered

0.80

ramid

0.77

akening

0.75

estern

0.73

atche

0.72

uthor

0.72

ointed

0.72

riors

0.70

eln

0.69

chan

0.68

Activations Density 0.052%

instances of words related to legal documents or processes

instances of the word "writ" and related terms indicating legal documents or actions

No Comments

No Known Activations