INDEX

Explanations

phrases related to identity, including theft and fraud

oai_token-act-pair · gpt-3.5-turbo

references to identity and its various implications

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

iths

-0.69

ittle

-0.69

oys

-0.67

 Pigs

-0.66

housing

-0.65

âķĲâķĲ

-0.65

baugh

-0.65

ithing

-0.62

 Spoon

-0.62

OOL

-0.61

POSITIVE LOGITS

entity

1.01

 identity

0.92

 Theft

0.92

 Identity

0.88

iosyncr

0.87

 identities

0.85

 è£ıè

0.83

 theft

0.78

phal

0.73

holder

0.71

Activations Density 0.030%

phrases related to identity, including theft and fraud

references to identity and its various implications

No Comments

No Known Activations