INDEX

Explanations

negations and quantifiers that often weaken assertions

oai_token-act-pair · gemini-2.0-flash

negation

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 disambiguazione

-0.78

 gyhoeddwyd

-0.62

MigrationBuilder

-0.57

 للاسماء

-0.57

Biographie

-0.57

 invokingState

-0.56

ValueGeneration

-0.56

PYX

-0.55

gatsby

-0.55

 Bourgoin

-0.55

POSITIVE LOGITS

 مرئيه

0.60

 everyone

0.56

 still

0.53

 people

0.50

enumi

0.50

 समीक्षाओं

0.50

now

0.50

 other

0.49

 مشين

0.49

 such

0.49

Activations Density 3.169%

negations and quantifiers that often weaken assertions

negation

No Comments

No Known Activations