INDEX

Explanations

sections of text with significant relevance or intensity

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

Junk characters and punctuation

np_acts-logits-general · gemini-2.0-flash

conditions ending in pathies using specific text structures

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

RenderAtEndOf

-0.55

_,

-0.47

________________

-0.46

off

-0.46

 Ibid

-0.46

-0.45

 halen

-0.45

ViewImports

-0.43

RDONLY

-0.43

sp

-0.43

POSITIVE LOGITS

:✨

0.94

 تكبرها

0.68

 crossorigin

0.63

]**

0.63

 useAppContext

0.63

دانشنامهٔ

0.62

matchCondition

0.62

[::-

0.62

 Wikimedijinoj

0.62

Activations Density 0.010%

sections of text with significant relevance or intensity

Junk characters and punctuation

conditions ending in pathies using specific text structures

No Comments

No Known Activations