INDEX

Explanations

references to various types of pipelines

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

-0.67

 major

-0.50

ban

-0.49

de

-0.49

mid

-0.48

er

-0.48

 link

-0.47

-0.46

complexType

-0.46

’

-0.45

POSITIVE LOGITS

1.03

 purpoſe

1.00

 Anſ

0.95

 pipelines

0.92

IntoConstraints

0.91

 houſe

0.90

 reaſon

0.90

 Diſ

0.87

 pipes

0.85

 preſent

0.85

Activations Density 0.121%

references to various types of pipelines

No Comments

No Known Activations