INDEX

Explanations

verbs and verbal phrases indicating actions or events

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

 ProtoMessage

-1.02

دانشنامهٔ

-0.98

SharedCtor

-0.93

 Jefus

-0.92

 Houſe

-0.89

 Monfieur

-0.89

 houſe

-0.88

 raiſ

-0.87

 Majefty

-0.86

InjectAttribute

-0.85

POSITIVE LOGITS

 worth

0.44

 rius

0.42

 urllib

0.40

 allowed

0.40

<!

0.38

or

0.38

 sure

0.37

.”

0.37

0.36

Activations Density 0.038%

verbs and verbal phrases indicating actions or events

No Comments

No Known Activations