INDEX

Explanations

references to specific locations or venues

oai_token-act-pair · gpt-3.5-turbo

possessive forms and references to locations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Reference

-0.77

insk

-0.72

_.

-0.70

Americans

-0.67

ocument

-0.66

eat

-0.66

BIP

-0.65

 assumes

-0.65

Reviewer

-0.65

India

-0.65

POSITIVE LOGITS

 outskirts

1.02

 Chinatown

1.00

 famed

1.00

 suburbs

0.94

 busiest

0.93

 rooft

0.92

 skyline

0.92

 finest

0.89

 streets

0.89

 bustling

0.87

Activations Density 0.115%

references to specific locations or venues

possessive forms and references to locations

No Comments

No Known Activations