INDEX

Explanations

phrases that involve expressions of speaking or stating

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Portail

-0.48

astéroïdes

-0.45

المناصب

-0.38

 ence

-0.36

 depositphotos

-0.34

 reaſon

-0.34

 quæ

-0.34

 talk

-0.34

 reafon

-0.33

noons

-0.33

POSITIVE LOGITS

 stating

1.87

 saying

1.69

 indicating

1.63

 pointing

1.60

 explaining

1.54

 suggesting

1.52

 noting

1.50

 describing

1.48

saying

1.46

 telling

1.44

Activations Density 0.377%

phrases that involve expressions of speaking or stating

No Comments

No Known Activations