INDEX

Explanations

evaluative language expressing opinions or judgments

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

-0.40

 esquecer

-0.40

 Rathaus

-0.39

 mål

-0.38

lot

-0.36

racene

-0.36

-0.35

過ご

-0.35

 oignons

-0.35

POSITIVE LOGITS

 NSCoder

0.92

 AssemblyVersion

0.90

 الرياضيه

0.90

ValueStyle

0.85

}],

0.84

CloseOperation

0.80

AccessorTable

0.77

Хьажоргаш

0.77

 ویکی‌پدی

0.77

'},

0.76

Activations Density 0.954%

evaluative language expressing opinions or judgments

No Comments

No Known Activations