INDEX

Explanations

expressions of enthusiasm or praise for people or things

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

positive sentiment/praise

np_max-act · gemini-2.0-flash Triggered by @johnny

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

1,048,576

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

COUVER

-0.55

 daraus

-0.55

AspNetCore

-0.50

Архівовано

-0.49

KeyCode

-0.49

 Réalisation

-0.49

 виправивши

-0.49

ंदीखरीदारी

-0.49

//};

-0.48

 toep

-0.48

POSITIVE LOGITS

 praises

1.20

 praising

1.14

 praise

0.93

 praised

0.84

 admiration

0.81

praise

0.81

MessageTagHelper

0.79

 Praise

0.77

Praise

0.76

 admiring

0.73

Activations Density 0.006%

expressions of enthusiasm or praise for people or things

positive sentiment/praise

No Comments

No Known Activations