INDEX

Explanations

numerical data or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 nomme

-0.50

 persons

-0.48

 angebra

-0.48

SEPT

-0.46

 stieg

-0.46

 odborn

-0.46

 спеціаль

-0.46

Lik

-0.44

ünst

-0.44

 tetrach

-0.43

POSITIVE LOGITS

+#+#

0.97

 kasarigan

0.89

MLLoader

0.83

setVerticalGroup

0.81

MigrationBuilder

0.80

 CreateTagHelper

0.80

 AssemblyCulture

0.79

DeleteBehavior

0.78

 cherchés

0.78

NameInMap

0.77

Activations Density 0.362%

numerical data or statistics

No Comments

No Known Activations