INDEX

Explanations

phrases related to political or ideological manipulation for personal gain

oai_token-act-pair · gpt-3.5-turbo

language related to exploitation for personal or political gain

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

DragonMagazine

-0.74

tackle

-0.72

TPPStreamerBot

-0.72

çīĪ

-0.68

etooth

-0.67

reflect

-0.66

 Trace

-0.65

ibr

-0.65

Bei

-0.62

CLOSE

-0.61

POSITIVE LOGITS

 profit

1.26

 agendas

1.12

 profits

1.11

 Profit

1.07

 gratification

1.04

 blackmail

1.02

 nefarious

1.00

 agenda

0.97

 predetermined

0.95

 advantage

0.94

Activations Density 0.577%

phrases related to political or ideological manipulation for personal gain

language related to exploitation for personal or political gain

No Comments

No Known Activations