INDEX

Explanations

references to numerical quantities or descriptions involving counts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 feux

-0.58

^(@)

-0.57

>{@

-0.57

 lumineux

-0.55

Toda

-0.54

nought

-0.54

 popolare

-0.54

 comet

-0.53

 nemico

-0.53

MLLoader

-0.53

POSITIVE LOGITS

InSection

0.84

TestingModule

0.74

 protoimpl

0.73

 Référence

0.68

SourceChecksum

0.62

 snippetHide

0.56

WebMethod

0.56

WebVitals

0.56

UserScript

0.55

Abitanti

0.54

Activations Density 0.092%

references to numerical quantities or descriptions involving counts

No Comments

No Known Activations