INDEX

Explanations

words related to legal professions or legal actions

oai_token-act-pair · gpt-3.5-turbo

terms related to legal and regulatory roles

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

©

-0.71

sterdam

-0.71

 understanding

-0.70

Politics

-0.65

sett

-0.65

 Adventures

-0.65

©¶æ

-0.64

GoldMagikarp

-0.63

¿½

-0.62

tags

-0.61

POSITIVE LOGITS

ium

0.97

itor

0.97

ious

0.94

ial

0.91

ially

0.89

berus

0.88

maid

0.86

IAL

0.84

essee

0.82

 sidx

0.81

Activations Density 0.026%

words related to legal professions or legal actions

terms related to legal and regulatory roles

No Comments

No Known Activations