INDEX

Explanations

terms related to administration and user management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 ISNI

-0.64

 особенно

-0.53

especially

-0.52

vábbi

-0.52

 surla

-0.51

zanas

-0.50

 especially

-0.49

Hentet

-0.49

 calore

-0.49

sendRedirect

-0.49

POSITIVE LOGITS

admin

1.01

 billions

0.84

 millions

0.77

millions

0.73

 Jesus

0.70

出版年

0.70

billion

0.70

billi

0.67

 EClass

0.67

 Millions

0.66

Activations Density 0.084%

terms related to administration and user management

No Comments

No Known Activations