INDEX

Explanations

phrases indicating support or alignment towards a particular position or group

oai_token-act-pair · gpt-3.5-turbo

references to different sides in a debate or conflict

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

initions

-0.85

iott

-0.80

ciating

-0.77

ãĤ¼ãĤ¦ãĤ¹

-0.73

yssey

-0.72

ctory

-0.71

issance

-0.70

untu

-0.70

ESCO

-0.69

ãģ®éŃĶ

-0.67

POSITIVE LOGITS

side

0.97

 side

0.96

 Side

0.91

kick

0.83

Side

0.76

Za

0.72

Kl

0.71

 seams

0.69

 sides

0.68

 plank

0.67

Activations Density 0.025%

phrases indicating support or alignment towards a particular position or group

references to different sides in a debate or conflict

No Comments

No Known Activations