INDEX

Explanations

food-related terms

oai_token-act-pair · gpt-3.5-turbo

keywords related to specific events or scheduled activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 lifetime

-0.56

 nucleus

-0.56

 session

-0.53

 fertile

-0.52

 charge

-0.52

 period

-0.51

 vacuum

-0.51

 core

-0.51

 cycle

-0.51

 step

-0.50

POSITIVE LOGITS

etheless

0.92

Berry

0.84

odore

0.82

gomery

0.82

romeda

0.81

anyahu

0.81

resa

0.81

withstanding

0.78

terness

0.78

swers

0.75

Activations Density 0.651%

food-related terms

keywords related to specific events or scheduled activities

No Comments

No Known Activations

food-related terms

keywords related to specific events or scheduled activities

No Comments

No Known Activations