INDEX

Explanations

requests for assistance or service

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

Precedes "to" or expresses desire

np_acts-logits-general · gemini-2.0-flash

want to / derivative of

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 Infórmanos

-0.70

roek

-0.58

 Roskov

-0.58

 existir

-0.55

AnchorTagHelper

-0.54

 först

-0.54

 layui

-0.53

UnusedPrivate

-0.51

WebVitals

-0.50

ukkig

-0.50

POSITIVE LOGITS

 something

0.73

 urgently

0.71

 quick

0.63

PasswordEncoder

0.60

__":

0.59

Sharper

0.58

Something

0.57

хьтан

0.57

 něco

0.57

something

0.56

Activations Density 0.177%

requests for assistance or service

Precedes "to" or expresses desire

want to / derivative of

No Comments

No Known Activations