INDEX

Explanations

terminology related to medical procedures and tumor pathology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_19/width_16k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.hook_mlp_out

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

SourceChecksum

-0.72

twimg

-0.59

nocache

-0.57

intios

-0.54

TagMode

-0.53

titleMargin

-0.51

 corri

-0.47

eafter

-0.47

ępnie

-0.46

 Reyn

-0.46

POSITIVE LOGITS

دانشنامهٔ

0.58

('@

0.56

StoryboardSegue

0.56

'@

0.55

 sinta

0.54

crivez

0.54

 released

0.51

 Wikimédia

0.50

 odkazy

0.50

released

0.49

Activations Density 1.270%

terminology related to medical procedures and tumor pathology

No Comments

No Known Activations