INDEX

Explanations

names of individuals involved in specific incidents

oai_token-act-pair · gpt-3.5-turbo

specific names of people and related incidents involving them

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

pse

-0.87

olkien

-0.84

 shaping

-0.84

 hitherto

-0.80

 Kyoto

-0.79

 Babel

-0.78

 translated

-0.78

 Nietzsche

-0.78

 Sanskrit

-0.78

 geopolitical

-0.77

POSITIVE LOGITS

 County

0.91

ville

0.91

 Police

0.91

 Correctional

0.91

 misdemeanor

0.88

 felony

0.85

 RCMP

0.84

 assailant

0.84

law

0.84

 defendants

0.84

Activations Density 0.763%

names of individuals involved in specific incidents

specific names of people and related incidents involving them

No Comments

No Known Activations