INDEX

Explanations

terms indicating levels or degrees of change or impact

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

TagHelper

-0.49

APIView

-0.47

ãy

-0.44

 somehow

-0.43

ıyors

-0.43

tableFuture

-0.42

sí

-0.42

Bac

-0.40

ArgsConstructor

-0.40

ực

-0.40

POSITIVE LOGITS

MigrationBuilder

0.98

 simplifié

0.80

ItemBackground

0.78

 disambiguazione

0.75

WithIOException

0.74

 improvement

0.73

 verbeter

0.73

ArrowToggle

0.73

bootstrapcdn

0.72

 Improvement

0.72

Activations Density 0.434%

terms indicating levels or degrees of change or impact

No Comments

No Known Activations