INDEX

Explanations

references to data manipulation and processing

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

followed by prepositions

np_acts-logits-general · gemini-2.0-flash

actions performed on data

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 otomatig

-0.91

LookAnd

-0.68

webElementXpaths

-0.59

Chooser

-0.59

 &___

-0.56

ViewFeatures

-0.54

PANY

-0.54

AttributeSet

-0.53

сунок

-0.53

 ویکی‌پدی

-0.52

POSITIVE LOGITS

by

0.80

 anew

0.75

 semula

0.74

 separately

0.72

 together

0.66

 accordingly

0.65

 into

0.65

 differently

0.63

 properly

0.62

 elsewhere

0.62

Activations Density 1.423%

references to data manipulation and processing

followed by prepositions

actions performed on data

No Comments

No Known Activations