INDEX

Explanations

references to specific locations or names associated with individuals or geographical entities

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

 Wiktionnaire

-0.77

 <=",

-0.74

发表于

-0.66

 jsPsych

-0.66

 الحره

-0.59

//

-0.57

 tslint

-0.57

 للمعارف

-0.57

ngOn

-0.55

 numerus

-0.54

POSITIVE LOGITS

 appunto

0.67

mergeFrom

0.60

Diwedd

0.59

 soldati

0.57

urlpatterns

0.53

 ahorrar

0.50

 définiti

0.49

 femininas

0.49

Pyx

0.48

hova

0.48

Activations Density 1.059%

references to specific locations or names associated with individuals or geographical entities

No Comments

No Known Activations