INDEX

Explanations

phrases that indicate grouping or classification within a context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

✨:

-0.65

 Heiden

-0.64

`<

-0.64

Zeneca

-0.64

 Xcode

-0.60

 Southeast

-0.60

__((

-0.60

}`).

-0.60

versy

-0.59

 Voltaire

-0.58

POSITIVE LOGITS

ReusableCell

0.78

 these

0.74

invokeLater

0.73

MathML

0.69

 član

0.68

 Protobuf

0.67

staande

0.67

 disambiguazione

0.66

 toilettes

0.66

ellige

0.63

Activations Density 0.107%

phrases that indicate grouping or classification within a context

No Comments

No Known Activations