INDEX

Explanations

quantitative information related to measurements or counts

oai_token-act-pair · gpt-3.5-turbo

phrases related to frequency and occurrence metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

anship

-0.76

¶æ

-0.66

achus

-0.64

aukee

-0.62

ACY

-0.62

gyn

-0.62

anamo

-0.61

thood

-0.60

otomy

-0.59

 concede

-0.58

POSITIVE LOGITS

 guiActiveUnfocused

0.83

 istg

0.73

 Sands

0.71

)",

0.66

soDeliveryDate

0.65

CS

0.63

 ______

0.61

 colours

0.60

 Clarks

0.60

 Vale

0.59

Activations Density 1.416%

quantitative information related to measurements or counts

phrases related to frequency and occurrence metrics

No Comments

No Known Activations