INDEX

Explanations

terms related to biological and genomic components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

roits

-0.56

pii

-0.52

้อ

-0.52

 alpina

-0.51

tv

-0.49

 białym

-0.48

 NSError

-0.47

 makam

-0.47

 alimento

-0.47

 gravure

-0.47

POSITIVE LOGITS

 totalSupply

0.85

 consisting

0.84

 roster

0.83

 للمعارف

0.80

Carrière

0.77

 fileList

0.74

 consists

0.73

 lineup

0.72

lijst

0.71

IsContent

0.68

Activations Density 0.968%

terms related to biological and genomic components

No Comments

No Known Activations