INDEX

Explanations

numerical data and metrics related to various subjects

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

Followed by digits or other characters

np_acts-logits-general · gemini-2.0-flash

digit 2

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

<eos>

-0.51

!(

-0.50

 special

-0.47

are

-0.45

sp

-0.44

DoubleQuotes

-0.42

 included

-0.42

 quang

-0.41

 blant

-0.41

 gained

-0.41

POSITIVE LOGITS

RegressionTest

0.74

IUrlHelper

0.74

 Мексичка

0.73

Autoritní

0.71

 surla

0.71

 ReactDOM

0.70

withstanding

0.69

^(@)

0.68

SourceChecksum

0.68

KURZBESCHREIBUNG

0.67

Activations Density 0.276%

numerical data and metrics related to various subjects

Followed by digits or other characters

digit 2

No Comments

No Known Activations