INDEX

Explanations

specific nouns and scientific terms related to economics or healthcare

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

Appears after a job title

np_acts-logits-general · gemini-2.0-flash

grams, units, and proper nouns

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

 themselves

-0.59

 itself

-0.57

 дописавши

-0.57

 سكانية

-0.55

ClientSize

-0.53

 GenerationType

-0.52

jgl

-0.50

Tazama

-0.50

 proprement

-0.49

 sarili

-0.48

POSITIVE LOGITS

ConstraintMaker

0.67

 Scientology

0.59

 kasarigan

0.59

 rhestr

0.57

 Agamemnon

0.57

sizeCache

0.57

 Biro

0.56

 Wikimédia

0.55

 Maradona

0.55

 pancreatitis

0.55

Activations Density 1.092%

specific nouns and scientific terms related to economics or healthcare

Appears after a job title

grams, units, and proper nouns

No Comments

No Known Activations