INDEX

Explanations

references to documentation material or related content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

Xna

-0.79

 Medvedev

-0.64

providedIn

-0.63

toPromise

-0.61

kv

-0.60

 Beasley

-0.60

eventbus

-0.59

Op

-0.59

 virus

-0.58

ing

-0.58

POSITIVE LOGITS

 documentation

2.44

 Documentation

2.37

Documentation

2.32

documentation

2.31

documented

1.63

 documented

1.54

 Dokumentation

1.49

 documenta

1.47

 documenting

1.42

Documented

1.41

Activations Density 0.074%

references to documentation material or related content

No Comments

No Known Activations