INDEX

Explanations

references to awards and recognitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.36.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

DispatchToProps

-0.41

XmlAccessType

-0.39

PROTOBUF

-0.37

 днем

-0.36

白天

-0.35

第一天

-0.35

 createSlice

-0.35

Normdaten

-0.35

msgSender

-0.34

parsedMessage

-0.34

POSITIVE LOGITS

 annual

3.64

annual

3.20

 yearly

3.08

Annual

3.08

 Annual

3.06

 annually

2.91

 ANNUAL

2.91

 anual

2.77

ANNUAL

2.66

 annuel

2.61

Activations Density 0.495%

references to awards and recognitions

No Comments

No Known Activations