INDEX

Explanations

elements related to quantifiable activity and data processing

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

followed by specific nouns

np_acts-logits-general · gemini-2.0-flash

specific noun pairings

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

setVerticalGroup

-0.83

WriteTagHelper

-0.76

principalColumn

-0.73

 numberOfRows

-0.72

Geplaatst

-0.68

FormTagHelper

-0.65

 ivelany

-0.64

ftagPool

-0.62

 HasFactory

-0.59

wahlen

-0.59

POSITIVE LOGITS

 cref

0.49

所需

0.46

ooga

0.44

inerja

0.44

所需的

0.44

גרת

0.43

 mobi

0.43

tigungs

0.42

 trico

0.42

meau

0.42

Activations Density 0.850%

elements related to quantifiable activity and data processing

followed by specific nouns

specific noun pairings

No Comments

No Known Activations