INDEX

Explanations

names of individuals and specific entities associated with them

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

kesmas

-0.48

jsxFileName

-0.44

 الرياضيه

-0.41

 tighter

-0.41

 contrats

-0.40

 shortlist

-0.39

 tight

-0.39

 Guinée

-0.39

 flair

-0.39

 интерьере

-0.39

POSITIVE LOGITS

IVEREF

0.58

évaluateur

0.54

AppCompat

0.51

')

0.49

'}),

0.48

"){

0.48

dafx

0.48

']],

0.47

ellido

0.47

 Majefty

0.46

Activations Density 0.367%

names of individuals and specific entities associated with them

No Comments

No Known Activations