INDEX

Explanations

phrases indicating functions or roles, particularly those that involve serving as or acting as something significant

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

 propOrder

-0.78

 Taktlose

-0.77

 Sanger

-0.77

 centrifug

-0.72

DataAnnotations

-0.69

 Atari

-0.69

cherichia

-0.69

 Valladolid

-0.68

:✨

-0.67

 wipers

-0.67

POSITIVE LOGITS

inghouse

0.69

ctid

0.69

"},

0.65

tifacts

0.63

+");

0.62

"),

0.62

 sederhana

0.62

px

0.62

ுக்கு

0.61

"],

0.61

Activations Density 0.151%

phrases indicating functions or roles, particularly those that involve serving as or acting as something significant

No Comments

No Known Activations