INDEX

Explanations

references to names or identifiers within text

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

хозяй

-0.65

şiv

-0.62

 referrerpolicy

-0.60

">*</

-0.59

apkamer

-0.59

źródło

-0.58

ctiveness

-0.57

NgModule

-0.56

edipus

-0.56

 виправивши

-0.55

POSITIVE LOGITS

__(/*!

0.78

0.66

 termica

0.65

Rujuakan

0.60

tagext

0.59

GraphicsUnit

0.59

ellyn

0.57

FunctionFlags

0.56

 defStyleAttr

0.56

 paham

0.56

Activations Density 0.000%

references to names or identifiers within text

No Comments

No Known Activations

references to names or identifiers within text

No Comments

No Known Activations