INDEX

Explanations

references to academic publishers and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

出了

-0.47

</u>

-0.43

이

-0.41

<0xF0>

-0.41

容

-0.41

属

-0.40

横

-0.40

postmedia

-0.40

円

-0.39

props

-0.39

POSITIVE LOGITS

 autorytatywna

0.89

 resourceCulture

0.84

MemoryWarning

0.84

ंदीखरीदारी

0.83

 BoxFit

0.78

出版年

0.77

#+#

0.76

tagHelperRunner

0.75

 חיצוניים

0.75

 مرئيه

0.75

Activations Density 0.097%

references to academic publishers and locations

No Comments

No Known Activations

references to academic publishers and locations

No Comments

No Known Activations