INDEX

Explanations

references to specific cases or conditions in a mathematical context

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

 للاسماء

-0.60

 case

-0.55

 evidence

-0.50

CONST

-0.48

 mío

-0.46

 clear

-0.46

 cases

-0.46

 esser

-0.44

 Dienst

-0.44

cases

-0.43

POSITIVE LOGITS

ThroughAttribute

0.86

NOPQRST

0.81

 BrowserModule

0.78

styleType

0.76

 FetchType

0.75

omeness

0.73

GEBURTSDATUM

0.71

 GenerationType

0.71

MergeFrom

0.71

sendRedirect

0.70

Activations Density 0.016%

references to specific cases or conditions in a mathematical context

No Comments

No Known Activations

references to specific cases or conditions in a mathematical context

No Comments

No Known Activations