INDEX

Explanations

references to objects or constructs that are newly created or initialized in programming

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

Negative Logits

*/),

-0.86

bewerken

-0.79

InputTagHelper

-0.75

...";

-0.74

bcryptjs

-0.74

*/;

-0.73

Contours

-0.73

CppMethod

-0.73

')")

-0.73

 виправивши

-0.72

POSITIVE LOGITS

 Pellegrini

0.53

 superiori

0.52

 Westfield

0.50

 exemplaire

0.47

 bonheur

0.47

 tensile

0.47

 dentelle

0.47

 lähe

0.47

 istruzioni

0.47

 Slee

0.46

Activations Density 0.019%

references to objects or constructs that are newly created or initialized in programming

No Known Activations