INDEX

Explanations

numerical data and statistics

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

Numbers enclosed in brackets

np_acts-logits-general · gemini-2.0-flash

journal citations and identifiers

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

bootstrapcdn

-0.90

:✨

-0.84

styleType

-0.79

ftagPool

-0.74

tanleria

-0.74

addCriterion

-0.67

 لينك

-0.66

 autorytatywna

-0.66

 externi

-0.66

 geslacht

-0.66

POSITIVE LOGITS

fit

0.50

0.46

seman

0.45

0.44

Ble

0.43

0.42

EmployeeId

0.42

Rhe

0.42

Activations Density 0.328%

numerical data and statistics

Numbers enclosed in brackets

journal citations and identifiers

No Comments

No Known Activations