INDEX

Explanations

people's names

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names of individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

entimes

-0.85

 forgiven

-0.76

 compounded

-0.72

 accelerated

-0.72

 allotted

-0.71

 tumult

-0.70

 stricter

-0.68

 enforced

-0.68

 suspending

-0.68

 ramifications

-0.67

POSITIVE LOGITS

Adams

1.09

Marie

1.02

Jones

1.01

Moore

0.97

Lee

0.96

Walker

0.96

Clark

0.96

0.95

Lyn

0.95

Davis

0.94

Activations Density 0.235%

people's names

proper nouns, particularly names of individuals

No Comments

No Known Activations