INDEX

Explanations

terms related to programming frameworks and libraries

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

metheus

-0.47

dotti

-0.47

 banda

-0.44

-0.43

 ImGui

-0.42

 that

-0.41

 MotionEvent

-0.40

La

-0.40

POSITIVE LOGITS

 disambiguazione

1.02

 pleaſure

0.96

 reaſon

0.95

 houſe

0.93

 Majefty

0.93

 ſtate

0.90

 Theſe

0.90

 ostavi

0.90

 itſelf

0.90

 ―――――

0.89

Activations Density 0.388%

terms related to programming frameworks and libraries

No Comments

No Known Activations