INDEX

Explanations

phrases that indicate the start or initiation of an action

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

"begin" or "began"

np_acts-logits-general · gemini-2.0-flash

beginning or starting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

acamata

-0.50

 Spreadsheet

-0.45

 Verkehrs

-0.45

nosaurus

-0.44

şört

-0.44

ỡng

-0.42

 vassal

-0.41

 TRAFFIC

-0.41

arache

-0.40

ضايا

-0.40

POSITIVE LOGITS

 Begin

0.98

 begins

0.95

 Begins

0.94

Begin

0.94

 begin

0.93

begins

0.92

 begun

0.90

 beginning

0.87

beginning

0.87

 Beginning

0.84

Activations Density 0.105%

phrases that indicate the start or initiation of an action

"begin" or "began"

beginning or starting

No Comments

No Known Activations