INDEX

Explanations

references to legal or formal language, often associated with rules and provisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 HasFactory

-0.98

 Magnetism

-0.86

 Sando

-0.85

 Audiodateien

-0.84

 charset

-0.83

Zit

-0.79

iddler

-0.77

AutoScaleMode

-0.77

 متعلقه

-0.76

 Montagu

-0.75

POSITIVE LOGITS

Pro

1.32

PRO

1.31

Pro

1.25

PRO

1.20

pro

1.06

 Prodi

0.99

 Prow

0.95

 Pros

0.93

 Proctor

0.92

プロ

0.91

Activations Density 0.289%

references to legal or formal language, often associated with rules and provisions

No Comments

No Known Activations