INDEX

Explanations

the presence of the prefix "un-" in words

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

starting with "Un"

np_acts-logits-general · gemini-2.0-flash

words starting with un

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 TAMBÉM

-0.57

oltre

-0.46

ISSION

-0.45

SFER

-0.45

ostringstream

-0.44

adau

-0.43

bka

-0.43

obenzene

-0.42

ης

-0.42

 törté

-0.41

POSITIVE LOGITS

Espèce

0.66

Personensuche

0.65

bootstrapcdn

0.65

 defaultstate

0.64

็จ

0.62

migrationBuilder

0.62

 ModelExpression

0.62

tagext

0.61

 onAnimation

0.61

MLLoader

0.61

Activations Density 0.123%

the presence of the prefix "un-" in words

starting with "Un"

words starting with un

No Comments

No Known Activations