INDEX

Explanations

terms related to characterization and the act of defining or describing traits

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

followed by "ization"

np_acts-logits-general · gemini-2.0-flash

characterization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 שוליים

-0.78

IBarButtonItem

-0.78

ArrowToggle

-0.75

 mergeFrom

-0.74

ężczy

-0.74

 citoy

-0.74

COUVER

-0.73

rivial

-0.72

borderSide

-0.72

ingale

-0.72

POSITIVE LOGITS

ization

0.82

 characters

0.68

isation

0.66

 traits

0.59

 Characters

0.59

istical

0.54

 COUN

0.53

izations

0.52

achter

0.52

Characters

0.52

Activations Density 0.089%

terms related to characterization and the act of defining or describing traits

followed by "ization"

characterization

No Comments

No Known Activations