INDEX

Explanations

phrases indicating comparison or assessment of quality

oai_token-act-pair · gpt-3.5-turbo

phrases indicating strength or intensity of actions or states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

":""},{"

-0.72

livious

-0.62

 moderator

-0.61

ctions

-0.61

Reviewer

-0.61

Coun

-0.60

aron

-0.60

UCT

-0.60

éĸ

-0.58

æ©

-0.57

POSITIVE LOGITS

 possibly

0.90

 feas

0.78

 Possible

0.71

 dared

0.69

 pleased

0.68

 practicable

0.65

bler

0.63

 reasonably

0.62

 wished

0.62

 tires

0.61

Activations Density 0.075%

phrases indicating comparison or assessment of quality

phrases indicating strength or intensity of actions or states

No Comments

No Known Activations