INDEX

Explanations

actions and processes related to improvement, evaluation, and adjustment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 houſe

-0.74

Eſ

-0.73

AxisAlignment

-0.73

 ſever

-0.72

 Jefus

-0.69

 Diſ

-0.69

 تضيفلها

-0.69

 ſeveral

-0.69

 Monfieur

-0.67

Efq

-0.67

POSITIVE LOGITS

脚注の使い方

0.74

__":

0.59

CGRectMake

0.59

 ול

0.59

 purposes

0.57

Рис

0.55

Бахар

0.54

ToAction

0.54

 ולה

0.53

</b>

0.53

Activations Density 0.632%

actions and processes related to improvement, evaluation, and adjustment

No Comments

No Known Activations