INDEX

Explanations

words related to legal actions and decisions

oai_token-act-pair · gpt-3.5-turbo

terms related to opinions and judgments in discussions or rulings

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

 oneself

-0.70

ãģĻ

-0.64

INTON

-0.61

ga

-0.61

omever

-0.61

soever

-0.61

 childbirth

-0.60

 Almighty

-0.60

AAAA

-0.60

 Pipe

-0.59

POSITIVE LOGITS

 spree

0.73

 woes

0.71

 manager

0.68

 foray

0.65

 extends

0.64

 crosses

0.63

 consists

0.63

ouf

0.62

 illustrates

0.62

eeds

0.62

Activations Density 0.281%

words related to legal actions and decisions

terms related to opinions and judgments in discussions or rulings

No Comments

No Known Activations