INDEX

Explanations

expressions of negation or the concept of "nothing."

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

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

HtmlAttribute

-0.70

 numberOfRows

-0.60

tonode

-0.59

 nonatomic

-0.56

Datuak

-0.56

 Majefty

-0.54

createClass

-0.54

 ivelany

-0.53

NameInMap

-0.53

AfterClass

-0.53

POSITIVE LOGITS

 nothing

0.84

nothing

0.78

FunctionFlags

0.77

 Nothing

0.75

 else

0.72

Nothing

0.72

 NOTHING

0.71

NOTHING

0.70

burger

0.63

 nakalista

0.61

Activations Density 0.064%

expressions of negation or the concept of "nothing."

No Comments

No Known Activations