INDEX

Explanations

government-related terms and policies

oai_token-act-pair · gpt-3.5-turbo

topics related to health, medical conditions, and public policy on healthcare

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Canaver

-0.84

agonist

-0.73

ictional

-0.61

cific

-0.60

erent

-0.57

monster

-0.57

 insider

-0.56

 Orig

-0.55

 Minotaur

-0.53

ociated

-0.52

POSITIVE LOGITS

etc

0.98

 subsidies

0.74

 pensions

0.68

 screenings

0.68

 reefs

0.62

 registrations

0.61

 clinics

0.61

 vacations

0.61

and

0.61

or

0.61

Activations Density 0.512%

government-related terms and policies

topics related to health, medical conditions, and public policy on healthcare

No Comments

No Known Activations