INDEX

Explanations

structures and syntax used in programming code

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

Code-related tokens and symbols

np_acts-logits-general · gemini-2.0-flash

code keywords and options

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

 pleins

-0.59

 épu

-0.56

ThemeOverlay

-0.55

Atsauces

-0.52

 laude

-0.51

forRoot

-0.51

if

-0.51

NewGuid

-0.49

 voisins

-0.49

 setw

-0.49

POSITIVE LOGITS

__:

0.89

$:

0.89

 <<<<<<<<<<<<<<

0.88

ⓘ

0.83

'':

0.81

_:

0.80

:✨

0.77

//

0.77

 “…

0.76

ViewFeatures

0.75

Activations Density 0.164%

structures and syntax used in programming code

Code-related tokens and symbols

code keywords and options

No Comments

No Known Activations