INDEX

Explanations

array and list data structure operations

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

"i" as loop variable

np_acts-logits-general · gemini-2.0-flash

loop counter i

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

principalTable

-0.58

OL

-0.46

Na

-0.45

dese

-0.45

${

-0.45

مان

-0.44

Des

-0.43

Ein

-0.43

 forma

-0.43

makeText

-0.43

POSITIVE LOGITS

iNdEx

0.88

 autorytatywna

0.85

enumi

0.83

Efq

0.82

 ddelweddau

0.77

ukunft

0.76

 tartalomajánló

0.75

 AssemblyCulture

0.73

CompilerServices

0.73

MLLoader

0.73

Activations Density 0.484%

array and list data structure operations

"i" as loop variable

loop counter i

No Comments

No Known Activations