INDEX

Explanations

structural formatting and notation in documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 bParam

-0.60

APORE

-0.59

 sponge

-0.58

 BorderRadius

-0.55

ṯ

-0.51

databind

-0.50

 NUKAT

-0.49

thier

-0.48

 Sponge

-0.48

hadoop

-0.47

POSITIVE LOGITS

addCriterion

0.58

modelBuilder

0.56

تقاوى

0.53

 gyhoeddwyd

0.52

CopyWith

0.52

RotationOrder

0.51

CompilerServices

0.50

 invokingState

0.50

knex

0.50

tonode

0.49

Activations Density 0.219%

structural formatting and notation in documents

No Comments

No Known Activations