INDEX

Explanations

mentions of options or configurations in a programming context

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

options

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 pelúcia

-0.48

 größten

-0.45

 elástica

-0.44

 getLast

-0.44

发表于

-0.43

GraphicsUnit

-0.41

IsContent

-0.41

rmtree

-0.41

QMetaType

-0.40

engagent

-0.40

POSITIVE LOGITS

 Options

1.16

Options

1.10

options

1.02

 options

0.99

OPTIONS

0.98

 OPTIONS

0.96

getOptions

0.88

 Option

0.87

Option

0.84

 OPTION

0.82

Activations Density 0.018%

mentions of options or configurations in a programming context

options

No Comments

No Known Activations