INDEX

Explanations

references to specific entities or organizations, particularly related to news or media

oai_token-act-pair · gpt-3.5-turbo

mentions of "New York."

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

ascript

-0.94

cius

-0.78

oglu

-0.75

ierrez

-0.73

inelli

-0.72

uddin

-0.69

chnology

-0.66

ONSORED

-0.66

osaurus

-0.66

orsi

-0.66

POSITIVE LOGITS

 York

1.11

 Zealand

0.99

bie

0.97

 Yorker

0.95

 YORK

0.94

 Orleans

0.94

bies

0.89

 Hampshire

0.89

 Testament

0.88

York

0.87

Activations Density 0.058%

references to specific entities or organizations, particularly related to news or media

mentions of "New York."

No Comments

No Known Activations