INDEX

Explanations

references to characters and their emotions or physical appearances

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

Preceding possessive pronouns/nouns

np_acts-logits-general · gemini-2.0-flash

his dissatisfaction

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

 diyor

-0.63

apunov

-0.63

 saya

-0.57

 chrétiens

-0.56

 nostru

-0.55

 enggak

-0.52

 citoyens

-0.52

 susten

-0.50

”!

-0.50

"!

-0.48

POSITIVE LOGITS

 hadn

0.87

Personensuche

0.75

IUrlHelper

0.73

 goddamn

0.71

دانشنامهٔ

0.69

 fucking

0.66

 stupidly

0.65

>--}}

0.65

webElement

0.64

 intptr

0.63

Activations Density 0.381%

references to characters and their emotions or physical appearances

Preceding possessive pronouns/nouns

his dissatisfaction

No Comments

No Known Activations