INDEX

Explanations

programming constructs related to data structure manipulation and control flow

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

Code-related symbols and operators

np_acts-logits-general · gemini-2.0-flash

real roots

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

didSet

-0.51

 Pompeii

-0.48

Conteúdo

-0.48

ulg

-0.48

torta

-0.47

 unlocks

-0.47

 téc

-0.46

crowd

-0.46

SequentialGroup

-0.46

 Namur

-0.45

POSITIVE LOGITS

 pinulongan

0.72

">//

0.65

parsedMessage

0.65

ContentAsync

0.61

WithIOException

0.59

 <=",

0.57

Aiheesta

0.56

ineno

0.55

Autoritní

0.55

dollis

0.54

Activations Density 0.339%

programming constructs related to data structure manipulation and control flow

Code-related symbols and operators

real roots

No Comments

No Known Activations