INDEX

Explanations

terms related to audio processing plugins and their features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

WriteBarrier

-0.62

 Chore

-0.46

 kiel

-0.44

 Bind

-0.44

Viitteet

-0.43

Cubit

-0.43

 interrom

-0.42

 coordination

-0.42

Intersect

-0.41

 bind

-0.41

POSITIVE LOGITS

 noise

0.76

 AssemblyTitle

0.75

 Noise

0.72

noise

0.70

évaluateur

0.70

 signal

0.69

Noise

0.69

 mergeFrom

0.68

peq

0.66

HandlerContext

0.66

Activations Density 0.820%

terms related to audio processing plugins and their features

No Comments

No Known Activations