INDEX

Explanations

specific terms associated with mathematical or legal concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

GEBURTSDATUM

-0.98

ymce

-0.91

>{@

-0.90

erializer

-0.84

IPAC

-0.82

principalTable

-0.79

PerformLayout

-0.77

曖昧さ回避

-0.76

 ✭✭

-0.76

 nahilalakip

-0.73

POSITIVE LOGITS

 itſelf

0.98

Autoritní

0.97

 Majefty

0.96

 Jefus

0.95

 whoſe

0.94

 myſelf

0.92

 ſtate

0.91

 becauſe

0.91

 poffe

0.91

 himſelf

0.90

Activations Density 1.777%

specific terms associated with mathematical or legal concepts

No Comments

No Known Activations