INDEX

Explanations

concepts related to biological classifications and categories

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

IVEREF

-0.59

 either

-0.55

Références

-0.54

either

-0.54

 Either

-0.53

RegressionTest

-0.53

 дописавши

-0.52



-0.50

Either

-0.50

OptionsMenu

-0.49

POSITIVE LOGITS

atouille

0.63

bootstrapcdn

0.61

édrale

0.57

räck

0.57

nloa

0.56

__':

0.56

MethodManager

0.55

SBATCH

0.55

__))

0.54

ConstraintMaker

0.54

Activations Density 0.217%

concepts related to biological classifications and categories

No Comments

No Known Activations