INDEX

Explanations

technical details and numerical information related to software or database specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

帖最后由

-0.74

Билгалдахарш

-0.69

ValueStyle

-0.67

 Akademi

-0.67

tanleria

-0.66

bootstrapcdn

-0.63

SourceChecksum

-0.63

 ISNI

-0.61

 InputDecoration

-0.61

хьтан

-0.60

POSITIVE LOGITS

iNdEx

0.50

top

0.47

addGap

0.44

bewerken

0.43

 ModelExpression

0.42

 >=",

0.42

Зноскі

0.41

 already

0.40

oneer

0.40

Top

0.40

Activations Density 0.481%

technical details and numerical information related to software or database specifications

No Comments

No Known Activations