INDEX

Explanations

terms related to identity, particularly in the context of theft and fraud

oai_token-act-pair · gpt-3.5-turbo

references to identity and its implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ittle

-0.78

baugh

-0.70

housing

-0.69

oys

-0.68

ovie

-0.67

iths

-0.67

neau

-0.64

ugal

-0.63

inging

-0.62

 elbows

-0.62

POSITIVE LOGITS

entity

1.09

 Theft

0.91

 identity

0.88

 Identity

0.85

 identities

0.82

 theft

0.80

iosyncr

0.78

phal

0.78

 Sakuya

0.74

ativity

0.74

Activations Density 0.033%

terms related to identity, particularly in the context of theft and fraud

references to identity and its implications

No Comments

No Known Activations