INDEX

Explanations

proper nouns of cities

oai_token-act-pair · gpt-3.5-turbo

references to various cities

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

New

-0.90

Qu

-0.89

-0.88

-0.87

POSITIVE LOGITS

Portland

1.71

Denver

1.71

Michigan

1.69

Toronto

1.66

Sov

1.64

Philadelphia

1.62

Baltimore

1.61

Alabama

1.61

Ohio

1.61

Minnesota

1.60

Activations Density 0.093%

proper nouns of cities

references to various cities

No Known Activations