INDEX

Explanations

references to continuous processes or activities

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

aarrggbb

-0.71

unhofer

-0.69

้ย

-0.69

 SDLK

-0.68

 mayors

-0.63

Biographie

-0.63

 Taft

-0.60

 gainera

-0.60

ssz

-0.59

gemeente

-0.58

POSITIVE LOGITS

 ongoing

1.39

Ongoing

1.29

ongoing

1.20

 Ongoing

1.18

 lauf

0.72

 underway

0.70

หว่าง

0.67

sont

0.61

 Bara

0.59

}';

0.59

Activations Density 0.053%

references to continuous processes or activities

No Comments

No Known Activations