INDEX

Explanations

programming constructs related to error handling and validation checks

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

Code-related special characters

np_acts-logits-general · gemini-2.0-flash

Papaya, were less, B106

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

Spoljašnje

-0.69

sizeCache

-0.60

spender

-0.59

findpost

-0.55

jskiej

-0.54

Zeneca

-0.54

redirects

-0.53

ogos

-0.53

 Fink

-0.52

Попис

-0.51

POSITIVE LOGITS

раздо

0.51

 transférez

0.48

 Maladies

0.48

0.47

άνι

0.46

endpush

0.44

 Wicidata

0.44

cmath

0.44

toggleClass

0.42

ことはありません

0.41

Activations Density 0.047%

programming constructs related to error handling and validation checks

Code-related special characters

Papaya, were less, B106

No Comments

No Known Activations