INDEX

Explanations

references to numerical measurements and units

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

Preceding ordinal numbers or parts of a whole

np_acts-logits-general · gemini-2.0-flash

quantifier noun sequences

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Week

-0.54

 Woche

-0.52

middag

-0.51

 week

-0.51

ListItemIcon

-0.49

Day

-0.48

No

-0.45

terday

-0.45

Durée

-0.44

Week

-0.43

POSITIVE LOGITS

 يتيمه

0.93

fjspx

0.87

 bezeichneter

0.84

SharedDtor

0.82

(!__

0.72

providedIn

0.71

 Савезне

0.69

annica

0.69

erialization

0.68

Gön

0.68

Activations Density 0.349%

references to numerical measurements and units

Preceding ordinal numbers or parts of a whole

quantifier noun sequences

No Comments

No Known Activations