INDEX

Explanations

mathematical expressions and formulas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

-0.65

 Иль

-0.62

 control

-0.61

kid

-0.60

Historio

-0.59

います

-0.58

userdetails

-0.58

глу

-0.57

nbsp

-0.57

off

-0.56

POSITIVE LOGITS

(\

2.44

}(\

1.73

{(\

1.59

(\

1.56

$(\

1.56

$(\

1.44

)(\

1.41

}(\

1.28

">(</

1.22

}}(\

1.21

Activations Density 0.231%

mathematical expressions and formulas

No Comments

No Known Activations