INDEX

Explanations

terms related to weakness or diminished strength

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

 Orrell

-0.68

Наводи

-0.65

Convey

-0.64

ToLeft

-0.63

 Gilman

-0.62

 fichero

-0.61

guenos

-0.61

amse

-0.59

 sonora

-0.57

 дописавши

-0.57

POSITIVE LOGITS

weak

0.87

 Weakness

0.86

 weakness

0.84

 Weak

0.84

 weakly

0.81

Weaknesses

0.78

 hoogte

0.77

 weak

0.73

Bb

0.69

Weakness

0.69

Activations Density 0.008%

terms related to weakness or diminished strength

No Comments

No Known Activations

terms related to weakness or diminished strength

No Comments

No Known Activations