INDEX

Explanations

references to torture and related inhumane treatment

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 propOrder

-0.82

тьяна

-0.68

 fréqu

-0.65

abetes

-0.64

Lien

-0.64

AnchorTagHelper

-0.59

DriverManager

-0.59

 ген

-0.58

stateProvider

-0.57

GEBRA

-0.57

POSITIVE LOGITS

 torture

1.42

 Torture

1.30

tort

1.15

 tortured

1.12

 tortura

1.09

 tort

1.05

Tort

1.03

 Tort

0.89

 TORT

0.85

 Cruel

0.77

Activations Density 0.010%

references to torture and related inhumane treatment

No Comments

No Known Activations