INDEX

Explanations

phrases indicating emotional engagement or personal reflections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

PhysRevLett

-0.59

metall

-0.45

<bos>

-0.45

writeField

-0.45

aram

-0.42

xam

-0.42

fassung

-0.41

lassen

-0.40

 Likewise

-0.40

 stomat

-0.40

POSITIVE LOGITS

ViewImports

1.01

AddTagHelper

0.89

 дописавши

0.84

MigrationBuilder

0.83

تقاوى

0.76

 Meksiku

0.75

ArrowToggle

0.74

 disambiguazione

0.73

IVEREF

0.72

 ostavi

0.71

Activations Density 0.358%

phrases indicating emotional engagement or personal reflections

No Comments

No Known Activations