INDEX

Explanations

specific numeric and descriptive elements within various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

AndEndTag

-0.91

AnchorStyles

-0.83

 ſche

-0.82

 Geſ

-0.80

 فريبيس

-0.75

 plufieurs

-0.75

">//

-0.74

 Geſch

-0.73

IntoConstraints

-0.73

ChildScrollView

-0.73

POSITIVE LOGITS

eb

0.37

bin

0.32

ad

0.32

list

0.31

cal

0.30

ech

0.30

 buck

0.29

pp

0.29

bay

0.29

Activations Density 5.303%

specific numeric and descriptive elements within various contexts

No Comments

No Known Activations