INDEX

Explanations

terms associated with matrix operations and optimizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

יי

-0.43

<eos>

-0.43

 ло

-0.43

 stories

-0.43

elang

-0.41

</h2>

-0.41

 doors

-0.40

誘

-0.40

Aç

-0.40

 bocca

-0.40

POSITIVE LOGITS

KommentareTeilen

0.94

 تانيه

0.94

 ModelExpression

0.92

 CreateTagHelper

0.90

 للمعارف

0.86

новниш

0.85

rrggbb

0.84

 سكانية

0.84



0.84

AxisAlignment

0.83

Activations Density 0.314%

terms associated with matrix operations and optimizations

No Comments

No Known Activations