INDEX

Explanations

programming keywords and symbols

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

Go code related to function definitions

np_acts-logits-general · gemini-2.0-flash

Go function definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 يتيمه

-0.95

 nahilalakip

-0.84

 AssemblyCulture

-0.74

astéroïdes

-0.69

 שוליים

-0.68

 تانيه

-0.65

WebVitals

-0.65

TintMode

-0.63

insee

-0.63

Архівовано

-0.61

POSITIVE LOGITS

func

0.75

 func

0.69

 type

0.64

type

0.61

VersionUID

0.59

 types

0.53

Kev

0.50

 functions

0.48

 chức

0.46

 TYPE

0.44

Activations Density 0.077%

programming keywords and symbols

Go code related to function definitions

Go function definitions

No Comments

No Known Activations