INDEX

Explanations

layout and styling attributes in a markup or coding context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/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.16.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

 houſe

-0.82

expandindo

-0.80

 betweenstory

-0.79

 Normdatei

-0.77



-0.77

enderror

-0.76

TileEntity

-0.73

دانشنامهٔ

-0.73

 Italijanski

-0.72

Hochspringen

-0.69

POSITIVE LOGITS

prus

0.50

rungsseite

0.49

 Cowan

0.46

гих

0.46

Column

0.45

 vertical

0.43

mekte

0.43

flex

0.42

weibo

0.42

 verticales

0.42

Activations Density 0.038%

layout and styling attributes in a markup or coding context

No Comments

No Known Activations