INDEX

Explanations

terms related to audio or video quality and artifacts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

ох

-0.51

RegressionTest

-0.49

GeneratedCode

-0.49

↵

-0.46

Shortcut

-0.46

+#+#

-0.45

toCharArray

-0.45

口

-0.44

complexType

-0.44

us

-0.44

POSITIVE LOGITS

 artifact

0.79

 artefacts

0.71

 artifacts

0.68

artifact

0.66

 Artifact

0.64

 arte

0.64

lag

0.59

 Arte

0.59

Демографія

0.58

niosek

0.58

Activations Density 0.725%

terms related to audio or video quality and artifacts

No Comments

No Known Activations