INDEX

Explanations

words related to confidentiality and privacy

oai_token-act-pair · gpt-3.5-turbo

references to sensitive topics or issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

AUT

-0.84

FIN

-0.76

mere

-0.73

 Wolver

-0.72

SN

-0.69

 Helsinki

-0.68

LOAD

-0.67

 Fall

-0.66

ARK

-0.66

 Hemp

-0.66

POSITIVE LOGITS

 sensitive

1.33

ivities

1.04

ensitive

0.94

sensitive

0.92

 sensitivity

0.92

ively

0.91

mble

0.89

itized

0.84

 sensit

0.84

 proble

0.81

Activations Density 0.013%

words related to confidentiality and privacy

references to sensitive topics or issues

No Comments

No Known Activations