INDEX

Explanations

document sections with specific numerical or computational information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Cæsar

-0.92

 purpoſe

-0.90

 Económica

-0.89

 becauſe

-0.84

 reaſon

-0.83

uſ

-0.83

 Majefty

-0.83

存于互联网档案馆

-0.82

 Jefus

-0.82

 whoſe

-0.82

POSITIVE LOGITS

bitField

0.50

 кӀ

0.47

Naissance

0.45

MigrationBuilder

0.44

on

0.41

യാ

0.41

andosi

0.41

 last

0.41

 протяжении

0.40

ɜ

0.40

Activations Density 0.020%

document sections with specific numerical or computational information

No Comments

No Known Activations