INDEX

Explanations

references to the term "nothing" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

Lens

-0.41

chließ

-0.41

 Rouse

-0.40

RCT

-0.40

epo

-0.40

__["

-0.40

 Doncaster

-0.40

iyaki

-0.39

kenalkan

-0.39

 verbal

-0.38

POSITIVE LOGITS

 nothing

1.23

 Nothing

1.23

nothing

1.20

Nothing

1.16

 NOTHING

1.16

NOTHING

1.05

 nothin

0.98

 anything

0.95

anything

0.91

 Anything

0.89

Activations Density 0.113%

references to the term "nothing" and its variations

No Comments

No Known Activations