INDEX

Explanations

instances where someone's position or stance on a particular matter is mentioned

oai_token-act-pair · gpt-3.5-turbo

references to a person's or organization's position or stance on various issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

rosso

-0.80

STON

-0.74

displayText

-0.74

ebook

-0.67

ilation

-0.64

oa

-0.63

 Flavoring

-0.63

 hypert

-0.61

ãĥ¼ãĥĨãĤ£

-0.61

 disapp

-0.60

POSITIVE LOGITS

 positions

1.22

 position

1.19

holders

1.05

holder

0.95

iton

0.86

 plank

0.83

quo

0.82

Position

0.81

position

0.79

idon

0.79

Activations Density 0.021%

instances where someone's position or stance on a particular matter is mentioned

references to a person's or organization's position or stance on various issues

No Comments

No Known Activations