INDEX

Explanations

technical terminology and component names related to audio sessions, settings, user interface elements, and data structure bindings

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

aarrggbb

-0.78

co

-0.74

 bien

-0.72

la

-0.71

 resourceCulture

-0.69

 autorytatywna

-0.68

qu

-0.68

con

-0.67

pri

-0.67

POSITIVE LOGITS

 myſelf

1.38

 pleaſure

1.29

 houſe

1.29

ſelves

1.24

 Majefty

1.22

 Monfieur

1.21

 purpoſe

1.20

 ſmall

1.20

ſelf

1.19

 ſeveral

1.18

Activations Density 0.653%

technical terminology and component names related to audio sessions, settings, user interface elements, and data structure bindings

No Comments

No Known Activations