INDEX

Explanations

large numbers of people or entities

oai_token-act-pair · gpt-3.5-turbo

references to large groups of people

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

agate

-0.72

iban

-0.70

ãĥ¤

-0.70

Interstitial

-0.66

heimer

-0.65

Delivery

-0.65

mentioned

-0.63

 Redemption

-0.62

nam

-0.62

cer

-0.62

POSITIVE LOGITS

 ILCS

0.97

ourced

0.80

ourcing

0.79

aires

0.73

rd

0.73

 upon

0.72

 kilometers

0.69

":"/

0.69

aire

0.69

 thousands

0.69

Activations Density 0.035%

large numbers of people or entities

references to large groups of people

No Comments

No Known Activations