INDEX

Explanations

indicators of significant numerical information, possibly related to scoring or measures in a competitive context

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

Programming code or mathematical expressions

np_acts-logits-general · gemini-2.0-flash

width:

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

 surla

-0.64

 otomatig

-0.63

 AssemblyCulture

-0.60

 initComponents

-0.59

Vidite

-0.53

Референце

-0.52

neux

-0.51

 للمعارف

-0.50

invokeLater

-0.48

ronique

-0.47

POSITIVE LOGITS

enumi

1.80

enumii

1.40

ientôt

0.59

 indépendante

0.58

 Anexo

0.57

 culte

0.56

 natale

0.56

internalType

0.56

enderror

0.55

RTLD

0.55

Activations Density 0.059%

indicators of significant numerical information, possibly related to scoring or measures in a competitive context

Programming code or mathematical expressions

width:

No Comments

No Known Activations