INDEX

Explanations

phrases indicating intention or desire to take action

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

 consultato

-0.61

RegistryLite

-0.59

SizeF

-0.55

 Maur

-0.54

InjectAttribute

-0.54

'{@

-0.54

 MaterialApp

-0.53

 disambiguazione

-0.53

 InputDecoration

-0.53

 nahilalakip

-0.53

POSITIVE LOGITS

 know

1.03

see

0.76

 knows

0.74

 graag

0.72

know

0.69

 wissen

0.68

be

0.65

Know

0.65

 tahu

0.65

 weten

0.63

Activations Density 0.132%

phrases indicating intention or desire to take action

No Comments

No Known Activations