INDEX

Explanations

phrases signaling credit or attribution

oai_token-act-pair · gpt-3.5-turbo

mentions of "Credit" associated with numerical values

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

 retard

-0.72

rency

-0.63

sembly

-0.62

terday

-0.62

 advoc

-0.62

 Lans

-0.61

estern

-0.60

 intest

-0.60

Kus

-0.59

 enlight

-0.59

POSITIVE LOGITS

 Provided

0.88

 CARD

0.83

card

0.74

Credit

0.72

Card

0.72

 Card

0.71

 Credit

0.71

 Cards

0.70

 Sources

0.69

giving

0.69

Activations Density 0.018%

phrases signaling credit or attribution

mentions of "Credit" associated with numerical values

No Comments

No Known Activations