INDEX

Explanations

cautionary language regarding sizing and warnings about suitability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

ZZI

-0.49

AudioManager

-0.46

беле

-0.46

RetentionPolicy

-0.44

nstein

-0.43

issauga

-0.43

$"

-0.42

,:]

-0.42

tigo

-0.41

sbury

-0.41

POSITIVE LOGITS

tagHelperRunner

0.87

writeField

0.86

 للاسماء

0.80

Personendaten

0.79

 الحره

0.77

 pinulongan

0.75

AnchorStyles

0.72

OGND

0.71

 AssemblyCulture

0.70

 typelib

0.69

Activations Density 0.160%

cautionary language regarding sizing and warnings about suitability

No Comments

No Known Activations