INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

proper nouns related to specific entities or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Boone

-0.82

 Tacoma

-0.71

 Milwaukee

-0.69

 Columbia

-0.68

Todd

-0.68

 Indiana

-0.67

 Asheville

-0.67

 Spokane

-0.67

 Amtrak

-0.67

 Wisconsin

-0.66

POSITIVE LOGITS

 Gaddafi

0.97

ghai

0.92

croft

0.88

 Sheikh

0.84

alys

0.84

Hua

0.84

 Programme

0.83

xit

0.83

 Malaysian

0.83

 Tayyip

0.81

Activations Density 0.968%

proper nouns

proper nouns related to specific entities or organizations

No Comments

No Known Activations