INDEX

Explanations

numerical ages or age-related terms

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

 }_{\

-0.53

\}

-0.50

ramas

-0.50

nsyn

-0.49

paya

-0.49

rama

-0.49

rost

-0.49

sol

-0.49

crumb

-0.47

barco

-0.47

POSITIVE LOGITS

0.72

 useParams

0.69

featureID

0.68

utilisons

0.66

SourceChecksum

0.64

 perfeita

0.63

Geplaatst

0.58

逅

0.58

 للاسماء

0.57

dafx

0.57

Activations Density 0.069%

numerical ages or age-related terms

No Comments

No Known Activations