INDEX

Explanations

numerical values and related symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90

Prompts (Dashboard)

24,576 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

 Infórmanos

-0.51

 bekijken

-0.50

 möj

-0.50

protoimpl

-0.46

Šaltiniai

-0.45

 Mejía

-0.44

 aceitar

-0.44

']],

-0.42

 Flücht

-0.42

}],

-0.41

POSITIVE LOGITS

 itſelf

0.66

 myſelf

0.63

 ſte

0.61

 houſe

0.60

 ſta

0.59

 ſche

0.56

 againſt

0.56

 himſelf

0.55

 verſ

0.55

 faſt

0.55

Activations Density 1.138%

numerical values and related symbols

No Comments

No Known Activations