INDEX

Explanations

technical terms relating to data processing and system functionality

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

 lenker

-0.56

исленность

-0.54

redient

-0.45

Erreferentziak

-0.44

oflavin

-0.44

最快更新

-0.41

 snippetHide

-0.41

Bibliographie

-0.41

Flammability

-0.40

 Riggs

-0.40

POSITIVE LOGITS

 tartalomajánló

0.63

دانشنامهٔ

0.48

 виправивши

0.48

parsedMessage

0.46

 للمعارف

0.46

tanleria

0.43

 wireType

0.43

setPointSize

0.42

httphttps

0.41

TagMode

0.40

Activations Density 0.030%

technical terms relating to data processing and system functionality

No Comments

No Known Activations