INDEX

Explanations

identifiers and keywords related to programming and data structures

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

Code snippets with operators

np_acts-logits-general · gemini-2.0-flash

assignments and operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

nodoc

-0.58

 المعيارى

-0.56

\@

-0.56

entan

-0.52

 Hoek

-0.49

]={

-0.48

 Pritchard

-0.47

erapeu

-0.47

]=="

-0.47

ophila

-0.46

POSITIVE LOGITS

setVerticalGroup

0.85

ConstraintMaker

0.80

*=

0.73

+=

0.73

-=

0.69

--;

0.69

 defaultstate

0.68

/=

0.65

RTDA

0.63

Espèce

0.62

Activations Density 0.097%

identifiers and keywords related to programming and data structures

Code snippets with operators

assignments and operations

No Comments

No Known Activations