INDEX

Explanations

segments that include structured elements or indicators of organization in text

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

Code and markup delimiters

np_acts-logits-general · gemini-2.0-flash

`aligned` with code delimiters

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SourceChecksum

-0.91

Hauptartikel

-0.75

NameInMap

-0.72

 nahilalakip

-0.71

fjspx

-0.71

 intptr

-0.70

UVWXYZ

-0.69

interopRequire

-0.65

AndEndTag

-0.65

errHandler

-0.65

POSITIVE LOGITS

 itſelf

0.72

 themſelves

0.72

 himſelf

0.71

 myſelf

0.68

 poffe

0.65

 alſo

0.63

 againſt

0.62

 theſe

0.62

 ſaid

0.61

 Suomessa

0.60

Activations Density 0.042%

segments that include structured elements or indicators of organization in text

Code and markup delimiters

`aligned` with code delimiters

No Comments

No Known Activations