INDEX

Explanations

mentions of geographical locations

oai_token-act-pair · gpt-3.5-turbo

references to specific locations or entities related to historical or cultural significance

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

maxwell

-0.96

owler

-0.81

cause

-0.76

allery

-0.75

okin

-0.71

wallet

-0.68

healthy

-0.68

wt

-0.68

ongs

-0.68

 wallets

-0.68

POSITIVE LOGITS

 Guer

1.12

 XIII

1.00

 Blanc

0.97

 FranÃ§

0.92

 Marse

0.92

 Libre

0.91

 Grande

0.89

 Serie

0.89

 Prin

0.89

 Portug

0.88

Activations Density 0.246%

mentions of geographical locations

references to specific locations or entities related to historical or cultural significance

No Comments

No Known Activations