INDEX

Explanations

updates or mentions of events and changes over time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 NUKAT

-0.63

TagMode

-0.63

 ifrån

-0.61

IntoConstraints

-0.58

 récents

-0.56

 виправивши

-0.55

aneous

-0.54

ngdoc

-0.54

 opérés

-0.52

клопе

-0.52

POSITIVE LOGITS

 reactiv

0.78

 revival

0.74

 revived

0.72

 revisit

0.71

 resur

0.70

 revi

0.69

 revive

0.64

 reviving

0.62

 revisited

0.62

 reac

0.62

Activations Density 0.421%

updates or mentions of events and changes over time

No Comments

No Known Activations