INDEX

Explanations

phrases and statements related to the position or viewpoint on a particular issue

oai_token-act-pair · gpt-3.5-turbo

references to positions or opinions on issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

cing

-0.83

Interstitial

-0.81

NetMessage

-0.77

ined

-0.70

sample

-0.69

 Sparkle

-0.67

Grant

-0.66

nova

-0.65

apy

-0.65

esters

-0.64

POSITIVE LOGITS

 stance

1.33

 stances

1.23

yip

1.00

 positions

0.83

olicy

0.83

 posture

0.82

 position

0.80

 reversal

0.79

 guiActiveUn

0.78

terday

0.74

Activations Density 0.010%

phrases and statements related to the position or viewpoint on a particular issue

references to positions or opinions on issues

No Comments

No Known Activations