INDEX

Explanations

phrases related to battles or conflicts between individuals or groups

oai_token-act-pair · gpt-3.5-turbo

references to conflicts or confrontations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Chart

-0.72

warming

-0.71

ascript

-0.71

ritical

-0.70

oun

-0.69

birth

-0.69

ocument

-0.69

Birth

-0.68

 Journals

-0.68

relation

-0.68

POSITIVE LOGITS

 hordes

1.02

 formidable

0.95

 challengers

0.95

 opponents

0.93

 opponent

0.92

 unbeat

0.92

 fellow

0.90

 adversity

0.90

 undefeated

0.88

 foes

0.87

Activations Density 0.189%

phrases related to battles or conflicts between individuals or groups

references to conflicts or confrontations

No Comments

No Known Activations