INDEX

Explanations

names of individuals involved in legal processes

oai_token-act-pair · gpt-3.5-turbo

references to legal and governmental processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 âĢ

-0.64

Â¶

-0.63

NYC

-0.62

ãĢį

-0.61

 [âĢ¦]

-0.59

âĢ

-0.58

[/

-0.57

</

-0.57

tha

-0.56

âĢ¦

-0.56

POSITIVE LOGITS

ĸļ

0.72

moil

0.69

alysed

0.67

autions

0.66

ascript

0.66

terday

0.65

 teasp

0.64

estern

0.64

aturdays

0.62

eals

0.61

Activations Density 1.287%

names of individuals involved in legal processes

references to legal and governmental processes

No Comments

No Known Activations