INDEX

Explanations

phrases that indicate negation or absence in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

RefNanny

-0.64

]--;

-0.60

🏿

-0.56

 disambiguazione

-0.56

OrWhiteSpace

-0.54

 ***/

-0.53

WriteTagHelper

-0.52

헌

-0.52

fx

-0.50

loon

-0.50

POSITIVE LOGITS

 such

0.76

 SUCH

0.69

such

0.68

Such

0.66

 solche

0.64

 Such

0.62

 solches

0.59

นั้น

0.56

Serializable

0.55

 solcher

0.53

Activations Density 0.583%

phrases that indicate negation or absence in various contexts

No Comments

No Known Activations