INDEX

Explanations

references to press conferences or news conferences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.33.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

adaptiveStyles

-0.69

StructEnd

-0.61

SharedCtor

-0.52

 Chwiliwch

-0.52

tonode

-0.51

 resourceCulture

-0.51

 terciopelo

-0.44

 noDo

-0.43

 ISNI

-0.43

inSlope

-0.43

POSITIVE LOGITS

 press

1.55

 Press

1.35

 PRESS

1.27

Press

1.26

press

1.23

 Presse

1.20

 briefing

1.14

 conference

1.10

 presse

1.07

記者

1.06

Activations Density 0.124%

references to press conferences or news conferences

No Comments

No Known Activations