INDEX

Explanations

references to publications and their details

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

RenderAtEndOf

-0.89

RegressionTest

-0.72

Vidite

-0.62

Искәрмәләр

-0.61

 lenker

-0.60

 AssemblyTitle

-0.58

DoubleQuotes

-0.55

viel

-0.54

InSection

-0.54

таратура

-0.52

POSITIVE LOGITS

tagHelperRunner

0.54

UnitTesting

0.51

 Wikiseite

0.51

SerializedName

0.48

complexType

0.48

 Dés

0.47

GetMapping

0.46

extAlignment

0.46

PASO

0.45

󠁿

0.45

Activations Density 0.065%

references to publications and their details

No Comments

No Known Activations