INDEX

Explanations

references to citation metrics or identifiers in academic contexts

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

DOI and numerical identifiers

np_acts-logits-general · gemini-2.0-flash

article citations and DOIs

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

ngdoc

-0.55

nonatomic

-0.54

Relative

-0.51

 professionale

-0.50

town

-0.49

 relative

-0.47

 ranked

-0.47

TOWN

-0.46

ђа

-0.45

edback

-0.45

POSITIVE LOGITS

 الحره

0.79

ItemBackground

0.70

enderror

0.69

 ISNI

0.58

abestanden

0.58

 SwitchCompat

0.57

 InputDecoration

0.57

 externs

0.56

Personendaten

0.55

HostException

0.55

Activations Density 0.152%

references to citation metrics or identifiers in academic contexts

DOI and numerical identifiers

article citations and DOIs

No Comments

No Known Activations