INDEX

Explanations

words related to legal action, investigations, or controversies

oai_token-act-pair · gpt-3.5-turbo

phrases related to criminal accusations and investigations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

arger

-0.71

 skelet

-0.67

<[

-0.65

âķĲ

-0.63

 anecd

-0.62

 UNCLASSIFIED

-0.61

:=

-0.58

pse

-0.58

espie

-0.57

 nerv

-0.57

POSITIVE LOGITS

 âĢİ

0.70

 [âĢ¦]

0.67

î

0.65

0.63

 Belfast

0.63

âĢİ

0.61

$.

0.57

hello

0.56

ADVERTISEMENT

0.56

 ....

0.55

Activations Density 3.659%

words related to legal action, investigations, or controversies

phrases related to criminal accusations and investigations

No Comments

No Known Activations