INDEX

Explanations

technical terms and operations related to file size and memory management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

-0.58

-0.49

-0.47

↵

-0.47

<eos>

-0.46

-0.45

-0.43

 High

-0.43

তথ্যসূত্র

-0.43

POSITIVE LOGITS

 purpoſe

1.01

 pleaſure

0.93

 cauſe

0.88

 Majefty

0.85

 auffi

0.83

 houſe

0.82

 poffible

0.82

 ſtate

0.82

 ſmall

0.78

 greateſt

0.77

Activations Density 0.606%

technical terms and operations related to file size and memory management

No Comments

No Known Activations