INDEX

Explanations

references to specific product features or sets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 مرئيه

-0.81

findpost

-0.76

onViewCreated

-0.70

 doInBackground

-0.66

 فريبيس

-0.64

DotNetBar

-0.62

TemporalType

-0.61

MigrationBuilder

-0.61

MethodImpl

-0.60

Erstellt

-0.60

POSITIVE LOGITS

set

1.75

 pack

1.73

 sets

1.63

Set

1.57

 package

1.56

セット

1.48

kit

1.47

 bundle

1.45

Set

1.40

 Pack

1.40

Activations Density 0.229%

references to specific product features or sets

No Comments

No Known Activations