INDEX

Explanations

numerical identifiers and structural details in a technical context

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

Mathematical formulas or code

np_acts-logits-general · gemini-2.0-flash

return or lineage

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

setVerticalGroup

-0.50

перь

-0.48

aima

-0.47

ómicas

-0.46

 мини

-0.45

 doble

-0.45

enschappelijke

-0.44

 prog

-0.44

これも

-0.43

Bibliographie

-0.43

POSITIVE LOGITS

PyExc

0.68

 Савезне

0.61

ContentAsync

0.60

 muualla

0.60

 vực

0.58

 szóci

0.58

odeon

0.58

bcryptjs

0.57

IsContent

0.57

 egyes

0.56

Activations Density 0.670%

numerical identifiers and structural details in a technical context

Mathematical formulas or code

return or lineage

No Comments

No Known Activations