INDEX

Explanations

proper nouns related to people or organizations

oai_token-act-pair · gpt-3.5-turbo

mentions of specific individuals or their influence

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

é¾

-0.76

quickShipAvailable

-0.75

dit

-0.74

RAFT

-0.71

 Aval

-0.65

FSA

-0.65

hered

-0.63

Leod

-0.63

ECTION

-0.63

reality

-0.62

POSITIVE LOGITS

adium

1.44

 Pall

1.16

adian

1.07

neum

0.88

oshenko

0.83

atre

0.82

amel

0.82

erva

0.81

asar

0.80

ograms

0.78

Activations Density 0.008%

proper nouns related to people or organizations

mentions of specific individuals or their influence

No Comments

No Known Activations