INDEX

Explanations

terms related to weapons and weaponry

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

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

 AssemblyCulture

-0.94

MemoryWarning

-0.81

 שוליים

-0.80

 solvable

-0.71

printStackTrace

-0.71

 disambiguazione

-0.70

 المعيارى

-0.70

 Paglinawan

-0.69

hoeddwyd

-0.69

 NSCoder

-0.68

POSITIVE LOGITS

ized

0.71

 instruments

0.58

arium

0.56

 Creature

0.56

Xna

0.55

 INSTRUMENTS

0.54

 assets

0.54

 Creatures

0.54

 Bernstein

0.52

instruments

0.51

Activations Density 0.261%

terms related to weapons and weaponry

No Comments

No Known Activations