INDEX

Explanations

specific formatting or symbols typically found in coding or mathematical expressions

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

 насељу

-0.45

onViewCreated

-0.44

ViewFeatures

-0.43

+#+#

-0.43

 tartalomajánló

-0.43

tagHelperRunner

-0.42

yntaxException

-0.42

 kasarigan

-0.42

 iVar

-0.41

 astore

-0.41

POSITIVE LOGITS

 lisäksi

0.50

 wyś

0.45

 alıntı

0.43

 Offisielt

0.41

Obrázky

0.41

abestanden

0.41

 genauso

0.40

同じく

0.40

 लेखक

0.40

EndContext

0.40

Activations Density 0.074%

specific formatting or symbols typically found in coding or mathematical expressions

No Comments

No Known Activations