INDEX

Explanations

references to future plans or intentions

oai_token-act-pair · gpt-3.5-turbo

references to future intentions or proposed actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 ILCS

-0.82

Cause

-0.82

INTON

-0.75

 Temper

-0.72

mint

-0.71

 Stain

-0.68

Interstitial

-0.68

inas

-0.65

gam

-0.65

iencies

-0.65

POSITIVE LOGITS

obs

0.90

 Parenthood

0.88

isphere

0.78

emaker

0.77

etary

0.77

 plans

0.75

escape

0.74

etting

0.74

 ahead

0.73

Activations Density 0.054%

references to future plans or intentions

references to future intentions or proposed actions

No Comments

No Known Activations