INDEX

Explanations

references to companies, groups, or organizations and their descriptions

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

pitched

-0.49

 mxArray

-0.45

feature

-0.44

gazette

-0.43

leth

-0.42

izoen

-0.42

 صوتيه

-0.41

wien

-0.41

 Stowe

-0.41

writeFieldEnd

-0.41

POSITIVE LOGITS

 conglomerate

0.72

集團

0.63

 subsidiaries

0.60

 Group

0.60

 Holdings

0.59

集团

0.57

 グループ

0.56

グループ

0.55

 GROUP

0.54

AnchorStyles

0.54

Activations Density 0.320%

references to companies, groups, or organizations and their descriptions

No Comments

No Known Activations