INDEX

Explanations

terms related to noise and sound levels

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 viață

-0.60

ständen

-0.55

AddColumn

-0.52

PhysRev

-0.50

kými

-0.49

Embed

-0.48

 façons

-0.48

 idéia

-0.48

gave

-0.48

 gången

-0.48

POSITIVE LOGITS

 Noise

0.82

mask

0.81

Noise

0.80

noise

0.78

 mask

0.76

 noise

0.76

Nak

0.75

 Mask

0.75

ыгана

0.74

 متعلقه

0.70

Activations Density 0.113%

terms related to noise and sound levels

No Comments

No Known Activations