INDEX

Explanations

news-related entities and actions

oai_token-act-pair · gpt-3.5-turbo

citations and reports of news events

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ĸļ

-1.09

uits

-0.77

pan

-0.73

mand

-0.70

cffffcc

-0.70

osate

-0.69

tnc

-0.68

uit

-0.68

sylvania

-0.68

xtap

-0.66

POSITIVE LOGITS

TMZ

1.01

 Insider

0.93

 sources

0.91

ESPN

0.89

 ESPN

0.89

 leaks

0.86

 Sports

0.85

 rumor

0.84

FOX

0.83

 exclusively

0.83

Activations Density 0.244%

news-related entities and actions

citations and reports of news events

No Comments

No Known Activations