INDEX

Explanations

phrases related to physical conflicts or confrontations

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate conflict or confrontation

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

 redistributed

-0.77

iture

-0.77

imate

-0.76

icter

-0.75

nosis

-0.75

bably

-0.72

overed

-0.71

SOURCE

-0.71

clips

-0.71

igmatic

-0.71

POSITIVE LOGITS

 regard

0.95

 regards

0.85

stood

0.77

 fellow

0.75

 coworkers

0.73

 neighbours

0.73

 creditors

0.73

 impunity

0.72

 mobs

0.70

 bandits

0.69

Activations Density 0.123%

phrases related to physical conflicts or confrontations

phrases that indicate conflict or confrontation

No Comments

No Known Activations