INDEX

Explanations

mathematical expressions and notations

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

APORE

-0.50

 Kupfer

-0.47

 mandat

-0.47

ς

-0.46

 cực

-0.46

[::-

-0.45

ervis

-0.45

ographique

-0.44

 Blvd

-0.43

POSITIVE LOGITS

verwijspagina

0.98

 handleMessage

0.75

 otomatig

0.69

 jsPsych

0.67

 kaarangay

0.63

rungsseite

0.63

assertRaises

0.62

UnknownFields

0.62

تقاوى

0.61

 SafeMath

0.60

Activations Density 0.314%

mathematical expressions and notations

No Comments

No Known Activations