INDEX

Explanations

words that refer to analysis, legal contexts, or in reference to

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.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

necedor

-0.73

in

-0.71

tagHelperRunner

-0.70

verwijspagina

-0.65

ใน

-0.63

 وتسجيلات

-0.63

ynchronously

-0.63

jmniej

-0.60

setLevel

-0.59

 Saltar

-0.59

POSITIVE LOGITS

 poveznice

0.59

pruch

0.54

CJK

0.53

 fashion

0.52

PRNewswire

0.52

 guise

0.52

 perpetuity

0.50

 hurry

0.49

 absence

0.49

 וב

0.49

Activations Density 0.737%

words that refer to analysis, legal contexts, or in reference to

No Comments

No Known Activations