INDEX

Explanations

references to objects or elements that are identifiable by specific attributes or values

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

UrlResolution

-0.58

bootstrapcdn

-0.54

 تضيفلها

-0.54

 pinulongan

-0.51

führ

-0.50

 alene

-0.50

批

-0.49

impulan

-0.49

permitAll

-0.49

 bhai

-0.48

POSITIVE LOGITS

 defaultstate

0.94

COUVER

0.70

 AssemblyTitle

0.70

CardContent

0.69

 createSlice

0.67

azol

0.65

anstalt

0.65

stalt

0.62

UnknownFieldSet

0.62

gameserver

0.61

Activations Density 0.000%

references to objects or elements that are identifiable by specific attributes or values

No Comments

No Known Activations