INDEX

Explanations

instances of the letter 'g'

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

Token "g" followed by specific words or abbreviations

np_acts-logits-general · gemini-2.0-flash

g words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

MessageOf

-0.52

 nahilalakip

-0.50

 stay

-0.48

 Stay

-0.48

ValueStyle

-0.47

 AspNetCore

-0.47

ifs

-0.46

entil

-0.46

stay

-0.45

 untere

-0.45

POSITIVE LOGITS

 onPostExecute

0.71

XmlAccessType

0.61

 jScrollPane

0.56

 SwitchCompat

0.54

 समीक्षक

0.53

 bezeichneter

0.52

 TextAlign

0.50

 awakeFromNib

0.50

$_['

0.49

ItemLayout

0.48

Activations Density 0.223%

instances of the letter 'g'

Token "g" followed by specific words or abbreviations

g words

No Comments

No Known Activations