INDEX

Explanations

specific numerical values or identifiers in data-related contexts

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

 EconPapers

-0.87

AddTagHelper

-0.82

EndContext

-0.81

 oprot

-0.80

########.

-0.80

ReusableCell

-0.79

cshtml

-0.76

 saites

-0.75

NameInMap

-0.72

?>/

-0.72

POSITIVE LOGITS

RegressionTest

0.53

UnitTesting

0.45

 Arkivert

0.44

kingen

0.44

AnimationsModule

0.44

MCG

0.43

Andra

0.41

ArgumentParser

0.39

 CCTV

0.39

setupUi

0.39

Activations Density 0.087%

specific numerical values or identifiers in data-related contexts

No Comments

No Known Activations