INDEX

Explanations

intensifiers indicating a high degree of emphasis or importance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Clik

-0.51

 excepción

-0.44

resizingMask

-0.43

 Side

-0.41

 GlobalKey

-0.39

responseType

-0.39

边的

-0.39

he

-0.38

اير

-0.38

 onPostExecute

-0.38

POSITIVE LOGITS

RegressionTest

1.05

MigrationBuilder

0.86

 المعيارى

0.85

 ostavi

0.84

 الرياضيه

0.81

ंदीखरीदारी

0.80

PerformLayout

0.79

AlterField

0.76

 bezeichneter

0.75

 Chwiliwch

0.75

Activations Density 0.244%

intensifiers indicating a high degree of emphasis or importance

No Comments

No Known Activations