INDEX

Explanations

code snippets or references related to web development scripts and libraries

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

Follows punctuation or special characters

np_acts-logits-general · gemini-2.0-flash

codes and identifiers

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

ARROLL

-0.49

TRIBUTION

-0.48

ÉD

-0.48

in

-0.47

ARROLLO

-0.47

 under

-0.46

 tartalomajánló

-0.43

elett

-0.43

❮

-0.43

the

-0.42

POSITIVE LOGITS

出版年

0.93

ⓧ

0.91

expandindo

0.86

Xna

0.82

 lenker

0.82

TypedDataSet

0.78

theless

0.77

+:+

0.76

DotNetBar

0.76

principalColumn

0.75

Activations Density 0.039%

code snippets or references related to web development scripts and libraries

Follows punctuation or special characters

codes and identifiers

No Comments

No Known Activations