INDEX

Explanations

elements of layouts in various contexts, particularly related to configuration in programming or visual design

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

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

 Andrews

-0.49

fiore

-0.48

 march

-0.47

 boutique

-0.47

 halv

-0.46

inhua

-0.45

ARANCE

-0.45

δε

-0.44

 dance

-0.44

 Shaw

-0.44

POSITIVE LOGITS

 system

2.52

System

2.40

 System

2.39

system

2.32

 SYSTEM

2.17

 systems

2.08

SYSTEM

1.96

 Systems

1.95

getSystem

1.94

ystem

1.93

Activations Density 0.123%

elements of layouts in various contexts, particularly related to configuration in programming or visual design

No Comments

No Known Activations