INDEX

Explanations

words related to "prolonged" or "pro" stemming forms in various contexts

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

 HasFactory

-0.98

 Audiodateien

-0.93

 charset

-0.85

 Sando

-0.81

 Magnetism

-0.79

Zit

-0.78

Fet

-0.78

iddler

-0.76

}{*}{}

-0.76

ukah

-0.75

POSITIVE LOGITS

Pro

1.37

PRO

1.35

Pro

1.28

PRO

1.24

pro

1.11

 Prodi

1.07

 Pros

1.00

 Prow

0.99

pro

0.92

プロ

0.92

Activations Density 0.286%

words related to "prolonged" or "pro" stemming forms in various contexts

No Comments

No Known Activations