INDEX

Explanations

specific code identifiers and notations used in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

ItemBackground

-0.58

rceil

-0.57

 Waray

-0.55

 propOrder

-0.54

IsMutable

-0.53

RoutingModule

-0.53

complexContent

-0.53

Coordonnées

-0.51

HasIndex

-0.49

 صوتيه

-0.48

POSITIVE LOGITS

Skocz

0.56

OPLE

0.52

 للمعارف

0.52

wiat

0.50

 genesis

0.50

zepte

0.49

Geplaatst

0.48

 particular

0.48

kia

0.47

はじめに

0.47

Activations Density 0.149%

specific code identifiers and notations used in programming contexts

No Comments

No Known Activations