INDEX

Explanations

formatted text elements or sections in documents, particularly those related to headers or subsections

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

Horizontal lines/separators in text

np_acts-logits-general · gemini-2.0-flash

special characters and scientific terms

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

—

-0.76

TagMode

-0.76

Архівовано

-0.71

 DbContext

-0.66

—”

-0.62

ЙТЕ

-0.61

……」

-0.61

)].

-0.59

plasia

-0.58

……。

-0.58

POSITIVE LOGITS

----------------

1.71

---------------

1.42

awtextra

1.30

//-

0.94

.-"

0.90

ˏ

0.89

➟

0.87

&-

0.87

-}

0.86

..-

0.86

Activations Density 0.579%

formatted text elements or sections in documents, particularly those related to headers or subsections

Horizontal lines/separators in text

special characters and scientific terms

No Comments

No Known Activations