INDEX

Explanations

sequences of characters or numerical patterns that appear within a structured format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

éron

-0.41

冤

-0.37

 דו

-0.34

 beri

-0.33

Money

-0.31

 Money

-0.31

imp

-0.31

Lf

-0.30

ч

-0.30

醋

-0.30

POSITIVE LOGITS

ScopeManager

0.93

featureID

0.93

MigrationBuilder

0.88

enderror

0.87

istoitu

0.82

DataAnnotations

0.82

rxjs

0.81

Jeografia

0.80

VersionUID

0.79

 ErrIntOverflow

0.78

Activations Density 0.776%

sequences of characters or numerical patterns that appear within a structured format

No Comments

No Known Activations