INDEX

Explanations

negations or expressions of absence in a technical or code-related context

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

Tokens before numbers

np_acts-logits-general · gemini-2.0-flash

numbers and identifiers

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

HomeAsUpEnabled

-0.67

 Nama

-0.56

 bcrypt

-0.52

conda

-0.52

fontName

-0.51

 prohibido

-0.50

 balanceOf

-0.50

flexGrow

-0.50

 laude

-0.49

 pagado

-0.49

POSITIVE LOGITS

<bos>

0.80

 propOrder

0.76



0.76

帖最后由

0.70

tagHelperRunner

0.66

 jadx

0.63

Попис

0.62

 оригіналу

0.61

IVEREF

0.61

saraba

0.59

Activations Density 1.033%

negations or expressions of absence in a technical or code-related context

Tokens before numbers

numbers and identifiers

No Comments

No Known Activations