INDEX

Explanations

terms related to scientific measurements and comparisons

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



-0.62

 latter

-0.61

 HasFactory

-0.59

reiras

-0.58

</i>

-0.58

ExecuteReader

-0.56

Datuak

-0.54

 pulumi

-0.54

ized

-0.53

kirchen

-0.53

POSITIVE LOGITS

NameInMap

0.88

RefNanny

0.75

CWE

0.74

*~*~

0.72

WebVitals

0.71

nextProps

0.71

serviceWorker

0.69

WithMany

0.69

المشاركات

0.68

ingale

0.67

Activations Density 0.820%

terms related to scientific measurements and comparisons

No Comments

No Known Activations