INDEX

Explanations

chunks or pieces of something

oai_token-act-pair · gpt-3.5-turbo

references to large quantities or significant portions of items

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

 Parade

-0.67

 Correspond

-0.67

 Mood

-0.66

âĢ¢âĢ¢âĢ¢âĢ¢

-0.64

ggles

-0.64

Adv

-0.62

 mood

-0.59

inen

-0.59

 prog

-0.59

Cou

-0.58

POSITIVE LOGITS

 chunks

1.20

 chunk

1.08

buster

0.94

dump

0.91

staking

0.86

iest

0.84

meal

0.81

eenth

0.79

busters

0.77

ies

0.77

Activations Density 0.007%

chunks or pieces of something

references to large quantities or significant portions of items

No Comments

No Known Activations