INDEX

Explanations

references to specific studies or data mentioned in a scientific context

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

хьтан

-0.56

 esternos

-0.54

ècie

-0.47

HasAnnotation

-0.45

YourGuide

-0.42

StructEnd

-0.42

 autorytatywna

-0.41

quehanna

-0.41

Tembelea

-0.40

ionario

-0.39

POSITIVE LOGITS

LookAnd

0.55

ScopeManager

0.46

prepareStatement

0.44

transQ

0.42

 Comfort

0.42

RegressionTest

0.41

Comfort

0.41

flashdata

0.40

Geplaatst

0.39

UrlResolution

0.38

Activations Density 0.742%

references to specific studies or data mentioned in a scientific context

No Comments

No Known Activations