INDEX

Explanations

phrases relating to main points, issues, and objectives in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 InputDecoration

-0.62

thető

-0.53

 tombé

-0.52

こちらも

-0.51

tigas

-0.50

 Biôgrafia

-0.50

 benzer

-0.49

 NDEBUG

-0.48

Dare

-0.47

 иначе

-0.47

POSITIVE LOGITS

 main

1.84

 principale

1.71

 principaux

1.57

 principal

1.55

 MAIN

1.52

 utama

1.49

 głów

1.48

 principales

1.47

main

1.46

 Main

1.44

Activations Density 0.260%

phrases relating to main points, issues, and objectives in various contexts

No Comments

No Known Activations