INDEX

Explanations

terms associated with statistical analysis and experiments

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

preceding conditions or qualifiers

np_acts-logits-general · gemini-2.0-flash

scientific and technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

#+#

-1.41

 snippetHide

-1.19

verwijspagina

-1.17

MigrationBuilder

-1.17

tanleria

-1.12

AndroidJUnit

-1.07

 AssemblyCulture

-1.06

 disambiguazione

-1.05

 propOrder

-1.05

ंदीखरीदारी

-1.05

POSITIVE LOGITS

0.52

etc

0.48

的情况下

0.46

 during

0.45

 until

0.42

 والتي

0.42

 into

0.41

 lainnya

0.41

Activations Density 2.870%

terms associated with statistical analysis and experiments

preceding conditions or qualifiers

scientific and technical contexts

No Comments

No Known Activations