INDEX

Explanations

terms related to cloning and duplication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

No

-0.48

-0.47

-0.44

-0.43

 tarvit

-0.43

 منظ

-0.42

AxisAlignment

-0.42

ř

-0.41

↵↵

-0.41

POSITIVE LOGITS

</tfoot>

0.96

 clone

0.93

 Clone

0.91

 clones

0.90

 يتيمه

0.89

MLLoader

0.88

 صوتيه

0.88

tagHelperRunner

0.87

__*/

0.85

 unknownFields

0.85

Activations Density 0.090%

terms related to cloning and duplication

No Comments

No Known Activations