INDEX

Explanations

concepts related to roles and functions in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

ſcher

-0.61

 ſind

-0.57

 Infórmanos

-0.57

setupUi

-0.56

 nakalista

-0.56

 disambiguazione

-0.53

脚注の使い方

-0.53

 Paglinawan

-0.52

 Geſch

-0.52

 ſein

-0.51

POSITIVE LOGITS

 sebuah

0.55

 Someone

0.53

 someone

0.53

 Sebuah

0.51

 Another

0.50

↵↵

0.49

Someone

0.48

 another

0.48

Another

0.47

Activations Density 2.896%

concepts related to roles and functions in various contexts

No Comments

No Known Activations

concepts related to roles and functions in various contexts

No Comments

No Known Activations