INDEX

Explanations

code related to data fetching and API calls

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

Code-related punctuation and symbols

np_acts-logits-general · gemini-2.0-flash

code function syntax

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

-0.83

Whilst

-0.76

 perchè

-0.76

-0.75

 Whilst

-0.74

chè

-0.70

-0.69

=""/>

-0.65

 sólo

-0.64

pò

-0.63

POSITIVE LOGITS

 ***!

0.72

}></

0.65

 Afterward

0.63

ValueStyle

0.60

 {}",

0.58

extAlignment

0.58

RegistryLite

0.55

!*\

0.55

Hochspringen

0.54

"}

0.53

Activations Density 0.039%

code related to data fetching and API calls

Code-related punctuation and symbols

code function syntax

No Comments

No Known Activations