INDEX

Explanations

constructions indicating the presence of negation or absence

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Cæsar

-1.11



-1.10

AutoScaleMode

-1.07

AsUp

-1.06

 Majefty

-1.02

 poffe

-1.01

windowFixed

-1.01

 itſelf

-1.01

aarrggbb

-1.01

 fubject

-1.00

POSITIVE LOGITS

no

1.15

 there

1.11

0.95

 some

0.93

 There

0.92

 plenty

0.90

there

0.85

Есть

0.85

There

0.84

 many

0.83

Activations Density 0.171%

constructions indicating the presence of negation or absence

No Comments

No Known Activations