INDEX

Explanations

proper nouns and technical terms related to telecommunications and places

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

featureID

-0.88

Personensuche

-0.83

bootstrapcdn

-0.81

MessageOf

-0.78

SourceChecksum

-0.73

(!__

-0.73

rungsseite

-0.72

 &___

-0.68

GEBURTSDATUM

-0.67

hoeddwyd

-0.66

POSITIVE LOGITS

 Majefty

0.74

 myſelf

0.63

 ſtate

0.60

 juſt

0.60

 pleaſure

0.60

 reaſon

0.59

σθαι

0.59

 Houſe

0.59

 Monfieur

0.58

 whoſe

0.58

Activations Density 0.589%

proper nouns and technical terms related to telecommunications and places

No Comments

No Known Activations