INDEX

Explanations

references to specific individuals and their roles in historical or notable contexts

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

 calendriers

-0.78

/>";

-0.71

//};

-0.60

]--;

-0.59

]";

-0.58

出版年

-0.58

SpringRunner

-0.58

findpost

-0.58

 Monfieur

-0.58

OGND

-0.57

POSITIVE LOGITS

 characters

0.64

 fictional

0.61

 Charakter

0.55

 Characters

0.51

 CHARACTERS

0.50

 الحره

0.50

 character

0.50

 karakter

0.49

 scenes

0.48

 omnis

0.48

Activations Density 1.002%

references to specific individuals and their roles in historical or notable contexts

No Comments

No Known Activations