INDEX

Explanations

punctuation marks and code syntax elements

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

verifyException

-0.62

-0.53

hen

-0.52

-0.48

 theo

-0.47

 appels

-0.47

 noDo

-0.47

sul

-0.46

チョコ

-0.46

 April

-0.46

POSITIVE LOGITS

 Majefty

0.88

 pleaſure

0.87

 greateſt

0.86

 ſmall

0.86

 Diſ

0.86

 ſtate

0.85

 houſe

0.84

 Jefus

0.82

 Houſe

0.81

 Shakspeare

0.81

Activations Density 0.006%

punctuation marks and code syntax elements

No Comments

No Known Activations