INDEX

Explanations

X-related terms often associated with scientific degrees and measurements

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

STC

-0.88

EndContext

-0.81

kháu

-0.71

يتر

-0.69

<tr>

-0.69

 onBind

-0.68

 Dred

-0.66

ostok

-0.66

SRS

-0.66

存于互联网档案馆

-0.65

POSITIVE LOGITS

 Phillies

1.35

Ph

1.31

Ph

1.27

Φ

1.18

PH

1.17

 Philo

1.17

PH

1.17

 Phillips

1.16

ph

1.15

Phaser

1.10

Activations Density 0.295%

X-related terms often associated with scientific degrees and measurements

No Comments

No Known Activations