INDEX

Explanations

instances of special formatting or structural elements in the text

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

Code, symbols, and unusual punctuation

np_acts-logits-general · gemini-2.0-flash

life technologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 quæ

-0.89

 ejus

-0.85

 eorum

-0.76

uſ

-0.75

 myſelf

-0.74

 auffi

-0.73

 theſe

-0.71

 chofe

-0.71

ArrowToggle

-0.71

 ſome

-0.71

POSITIVE LOGITS

0.56

BorderFactory

0.50

 BoxFit

0.50

 ángeles

0.48

 […]

0.47

HtmlAttribute

0.47

 appunto

0.47

ExtendWith

0.46

́

0.46

Activations Density 0.250%

instances of special formatting or structural elements in the text

Code, symbols, and unusual punctuation

life technologies

No Comments

No Known Activations