INDEX

Explanations

dates or personal names in news articles

oai_token-act-pair · gpt-3.5-turbo

specific dates and publication information from articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Wander

-0.70

 resin

-0.66

 destro

-0.66

roman

-0.65

 sucker

-0.65

 clamp

-0.62

 creep

-0.61

 mull

-0.61

 extortion

-0.61

ersen

-0.60

POSITIVE LOGITS

Associated

0.96

Country

0.93

Narr

0.86

Iss

0.85

Department

0.85

Member

0.85

Contribut

0.84

Summary

0.82

Eth

0.82

News

0.81

Activations Density 0.255%

dates or personal names in news articles

specific dates and publication information from articles

No Comments

No Known Activations