INDEX

Explanations

phrases indicating continuous or repeated actions

oai_token-act-pair · gpt-3.5-turbo

the repeated use of the word "keep" and its variations

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

DragonMagazine

-0.69

acus

-0.68

atana

-0.68

KEN

-0.66

ynski

-0.64

externalActionCode

-0.63

ooter

-0.63

 GOODMAN

-0.63

ode

-0.63

Interstitial

-0.63

POSITIVE LOGITS

 tabs

1.12

 pace

0.96

 afloat

0.94

 track

0.93

 secrets

0.91

 vigil

0.84

tracks

0.79

 alive

0.78

 secret

0.76

trap

0.72

Activations Density 0.043%

phrases indicating continuous or repeated actions

the repeated use of the word "keep" and its variations

No Comments

No Known Activations