INDEX

Explanations

coding constructs, particularly those related to conditionals and commands in scripts

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

Code snippets using sed

np_acts-logits-general · gemini-2.0-flash

shell script 'sed' commands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 propOrder

-0.78

transQ

-0.54

super

-0.46

unf

-0.44

zość

-0.43

zarchiwizowane

-0.43

úng

-0.43

REME

-0.42

autorité

-0.42

uper

-0.42

POSITIVE LOGITS

contentLoaded

0.80

CloseOperation

0.57

 ostavi

0.55

nonumber

0.52

AutoScaleMode

0.51

MENAFN

0.51

 fórmula

0.51

intrag

0.51

:✨

0.50

onViewCreated

0.50

Activations Density 0.202%

coding constructs, particularly those related to conditionals and commands in scripts

Code snippets using sed

shell script 'sed' commands

No Comments

No Known Activations