INDEX

Explanations

elements related to legal or technical terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 ComVisible

-0.68

 referenties

-0.66

 BoxDecoration

-0.63

 MessageBoxIcon

-0.60

+:+

-0.58

 متعلقه

-0.56

بوابة

-0.55

 gynhyrchwyd

-0.54

 Мексичка

-0.54

RegressionTest

-0.54

POSITIVE LOGITS

bastien

0.51

vellous

0.49

ruitt

0.48

طبيق

0.48

سجيل

0.48

وزيع

0.46

قرير

0.46

te

0.45

 Liefer

0.44

خطيط

0.44

Activations Density 0.064%

elements related to legal or technical terminology

No Comments

No Known Activations