INDEX

Explanations

expressions of desire or need

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

followed by "to" indicating intention

np_acts-logits-general · gemini-2.0-flash

desire or need to act

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

 intptr

-0.70

angering

-0.61

<%=

-0.60

iniums

-0.58

IDENTAL

-0.58

Köszönöm

-0.55

ItemBackground

-0.55

ciless

-0.54

cokinetic

-0.53

Portail

-0.53

POSITIVE LOGITS

tagHelperRunner

0.66

of

0.54

dalen

0.51

 célèbres

0.50

 الرياضيه

0.49

 Drill

0.49

Inflater

0.48

lief

0.47

 تضيفلها

0.47

oa̍t

0.47

Activations Density 0.414%

expressions of desire or need

followed by "to" indicating intention

desire or need to act

No Comments

No Known Activations