INDEX

Explanations

proper nouns and names

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

 Theſe

-0.52

 Beſ

-0.51

ECAUSE

-0.50

 Longo

-0.50

zke

-0.49

 neutre

-0.46

 Reſ

-0.46

 leaſt

-0.46

marvin

-0.46

 Houſe

-0.45

POSITIVE LOGITS

 AssemblyProduct

0.70

BeginContext

0.68

انيف

0.67

 Signalez

0.66

 mouseY

0.66

AndEndTag

0.66

tagHelperRunner

0.63

 חיצוניים

0.63

@[

0.61

IsMutable

0.61

Activations Density 0.326%

proper nouns and names

No Comments

No Known Activations