INDEX

Explanations

references to specific names or entities like "Fawcett," "Vishal," and "Mousavi."

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names related to individuals and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 situ

-0.66

ital

-0.65

Reviewed

-0.64

Quote

-0.62

 Patriarch

-0.62

Quotes

-0.60

EDIT

-0.60

ECH

-0.60

 Spending

-0.59

mobi

-0.59

POSITIVE LOGITS

Faw

0.98

ringe

0.95

acies

0.93

ulner

0.92

andom

0.88

ayette

0.87

ullah

0.86

ahon

0.85

ilipp

0.85

lling

0.85

Activations Density 0.014%

references to specific names or entities like "Fawcett," "Vishal," and "Mousavi."

proper nouns, specifically names related to individuals and organizations

No Comments

No Known Activations