INDEX

Explanations

punctuation marks and their frequencies within the text

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

symbols and abbreviations

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.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

تقاوى

-0.81

 ſche

-0.66

LookAnd

-0.64

ListItemIcon

-0.64

 يتيمه

-0.61

Chham

-0.60

parsedMessage

-0.59

دانشنامهٔ

-0.58

ItemBackground

-0.57

ThemeOverlay

-0.56

POSITIVE LOGITS

 lombok

0.52

 burung

0.37

 pisau

0.34

 sonriente

0.34

cyj

0.34

 deberían

0.34

 acronym

0.33

 füllen

0.32

meyen

0.32

 derra

0.31

Activations Density 0.000%

punctuation marks and their frequencies within the text

symbols and abbreviations

No Comments

No Known Activations