INDEX

Explanations

locations related to Washington, D.C

oai_token-act-pair · gpt-3.5-turbo

mentions of Washington, D.C

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

natureconservancy

-0.68

inarily

-0.67

olor

-0.62

------------------------

-0.62

resso

-0.62

 Helpful

-0.62

 href

-0.62

ï¸ı

-0.62

 VIDEOS

-0.61

>>\

-0.61

POSITIVE LOGITS

clinton

0.81

DC

0.77

 Janeiro

0.75

ĸļ

0.73

bourg

0.72

 Reagan

0.67

itzer

0.67

 Nevada

0.65

lich

0.65

 Lumpur

0.64

Activations Density 0.100%

locations related to Washington, D.C

mentions of Washington, D.C

No Comments

No Known Activations