INDEX

Explanations

numeric values and comparisons within data-driven contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 disambiguazione

-1.01

EDEFAULT

-0.95

featureID

-0.95

WithIOException

-0.76

twimg

-0.75

 AssemblyCulture

-0.75

UnusedPrivate

-0.74

ConstraintMaker

-0.74

 HasFactory

-0.72

homonymie

-0.70

POSITIVE LOGITS

tır

0.50

ともに

0.47

 currently

0.47

 enabled

0.46

 combination

0.46

 developed

0.46

El

0.43

 integrated

0.43

&=&\

0.42

Activations Density 0.322%

numeric values and comparisons within data-driven contexts

No Comments

No Known Activations