INDEX

Explanations

HTML header tags and specific notation elements in content

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

Mathematical notation delimiters (\[ and \])

np_acts-logits-general · gemini-2.0-flash

academic references and labels

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

ing

-1.30

ة

-0.88

ING

-0.81

ς

-0.80

en

-0.67

ní

-0.64

GLOBALS

-0.64

CardType

-0.62

Parameteri

-0.62

es

-0.60

POSITIVE LOGITS

<h1>

1.11

/>";

0.93

../../

0.82

ization

0.79

{}".

0.78

🔥🔥

0.74

częściej

0.73

siery

0.73

>"+

0.72

Kapcsolódó

0.72

Activations Density 0.282%

HTML header tags and specific notation elements in content

Mathematical notation delimiters (\[ and \])

academic references and labels

No Comments

No Known Activations