INDEX

Explanations

terms related to data processing and systems interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 Jefus

-0.81

 ſever

-0.80

Efq

-0.80

 Diſ

-0.79

Eſ

-0.78

 ſeveral

-0.77

 houſe

-0.77

ſelves

-0.71

 pleaſure

-0.71

 chofe

-0.69

POSITIVE LOGITS

脚注の使い方

0.74

Бахар

0.65

addPreferredGap

0.62

enumi

0.61

 purposes

0.57

Рис

0.57

</b>

0.56

CONCURRENT

0.54

\{\\

0.54

})}$

0.54

Activations Density 0.678%

terms related to data processing and systems interactions

No Comments

No Known Activations