INDEX

Explanations

testing-related assertions and their respective results

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.53

-0.49

-0.47

edo

-0.47

lasyon

-0.47

die

-0.46

ra

-0.46

fatalError

-0.45

con

-0.45

th

-0.44

POSITIVE LOGITS

 Signalez

0.95

 فريبيس

0.94

 quæ

0.94

 myſelf

0.92

 houſe

0.92

Efq

0.91

 Majefty

0.87

 purpoſe

0.86

 reaſon

0.83

 RIPRODUZIONE

0.82

Activations Density 0.184%

testing-related assertions and their respective results

No Comments

No Known Activations