INDEX

Explanations

discussions around beliefs and decisions

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

followed by "about" or related words

np_acts-logits-general · gemini-2.0-flash

says/talks about

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

enumi

-0.77

 parseFrom

-0.67

ReusableCell

-0.66

InvalidProtocol

-0.60

canf

-0.58

PointerException

-0.57

 hindurch

-0.56

\{\\

-0.56

GEBURTSDATUM

-0.56

DockStyle

-0.54

POSITIVE LOGITS

 about

2.80

about

2.01

About

1.79

 ABOUT

1.73

 About

1.70

 tentang

1.47

abt

1.27

ABOUT

1.24

 apie

1.20

 bout

1.16

Activations Density 0.446%

discussions around beliefs and decisions

followed by "about" or related words

says/talks about

No Comments

No Known Activations