INDEX

Explanations

marker symbols or related contextual elements in datasets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 optique

-0.50

you

-0.45

 each

-0.45

الو

-0.45

 μέ

-0.44

 économiques

-0.44

Hauptartikel

-0.43

วก

-0.43

 communautaire

-0.43

 cloud

-0.42

POSITIVE LOGITS

 Meksiku

1.17

 '\\;'

0.98

 betweenstory

0.89

MessageOf

0.86

LookAnd

0.86

WithIOException

0.85

oredCriteria

0.85

MigrationBuilder

0.85

WarningLevel

0.83

Gambas

0.80

Activations Density 0.303%

marker symbols or related contextual elements in datasets

No Comments

No Known Activations