INDEX

Explanations

occurrences of specific alphanumeric codes or identifiers

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

Acronyms/abbreviations, often two capital letters

np_acts-logits-general · gemini-2.0-flash

abbreviation followed by suffix

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 дописавши

-0.93

ViewImports

-0.80

WriteBarrier

-0.78

 autorytatywna

-0.78

]")]

-0.78

RenderAtEndOf

-0.77

Tetapi

-0.72

 propOrder

-0.70

 виправивши

-0.70

HostException

-0.68

POSITIVE LOGITS

0.57

 protoimpl

0.54

Me

0.54

Th

0.53

ion

0.53

0.52

gon

0.51

Ex

0.50

<em>

0.50

Activations Density 0.567%

occurrences of specific alphanumeric codes or identifiers

Acronyms/abbreviations, often two capital letters

abbreviation followed by suffix

No Comments

No Known Activations