INDEX

Explanations

references to choices or alternatives available in a context

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

"Option" or "Options"

np_acts-logits-general · gemini-2.0-flash

option or options

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 bezeichneter

-0.78

ymas

-0.76

]='\

-0.76

CrossRef

-0.73

BeginContext

-0.73

XmlAccessorType

-0.65

#+#

-0.64

PerformLayout

-0.63

signable

-0.63

 rendus

-0.62

POSITIVE LOGITS

 options

1.61

 Options

1.54

 option

1.45

 OPTION

1.37

options

1.36

 OPTIONS

1.30

 Option

1.27

Options

1.25

option

1.21

OPTION

1.19

Activations Density 0.132%

references to choices or alternatives available in a context

"Option" or "Options"

option or options

No Comments

No Known Activations