INDEX

Explanations

categories related to various forms of media, primarily focusing on the organization and classification of information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 Italijani

-0.80

enderror

-0.77

PreferredItem

-0.72

PYX

-0.72

principalColumn

-0.71

 myſelf

-0.69

 MainAxisSize

-0.68

}$)

-0.65

...');

-0.63

EDEFAULT

-0.62

POSITIVE LOGITS

semantics

0.58

null

0.41

arc

0.41

 Secondly

0.40

kust

0.39

enterOuterAlt

0.38

undefined

0.38

дар

0.38

gé

0.38

 Reagents

0.37

Activations Density 0.928%

categories related to various forms of media, primarily focusing on the organization and classification of information

No Comments

No Known Activations