INDEX

Explanations

instances of code-related operations and data interactions

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

Code with loop counters (i, j)

np_acts-logits-general · gemini-2.0-flash

for loop index

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

thâu

-0.78

ագրություններ

-0.77

 Roskov

-0.74

----</

-0.72

']=='

-0.71

 '\\;'

-0.71

脚注の使い方

-0.71

enderror

-0.71

 समीक्षाओं

-0.71

 חיצוניים

-0.70

POSITIVE LOGITS

NOPQRST

0.51

0.43

λικά

0.42

initComponents

0.42

ện

0.40

 accedere

0.40

 vivement

0.40

;;)

0.39

BorderLayout

0.39

addPreferredGap

0.39

Activations Density 0.018%

instances of code-related operations and data interactions

Code with loop counters (i, j)

for loop index

No Comments

No Known Activations