INDEX

Explanations

mathematical expressions and symbols related to functions and variables

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

</em>

-0.62

 esterni

-0.60

</strong>

-0.56

 gefü

-0.56

phrag

-0.55

gefü

-0.52

Décès

-0.49

beek

-0.48

 extré

-0.48

 racc

-0.47

POSITIVE LOGITS

 كومونز

1.01

(&:

0.99

ModelSerializer

0.99

 AttributeSet

0.97

 HasFactory

0.92

 للمعارف

0.90

pausal

0.88

(__('

0.86

Personendaten

0.86

 lenker

0.86

Activations Density 1.191%

mathematical expressions and symbols related to functions and variables

No Comments

No Known Activations