INDEX

Explanations

elements related to numerical data and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

</i>

-0.88

InstrumentedTest

-0.77

numerusform

-0.65

</b>

-0.63

 محفوظة

-0.62

AndEndTag

-0.61

 EnglishChoose

-0.58

omeness

-0.57

 ElementRef

-0.55

icoot

-0.55

POSITIVE LOGITS

AddTagHelper

0.78

Personensuche

0.77

SourceChecksum

0.72

())))

0.65

millimeters

0.65

…

0.61

ItemBackground

0.61

()))

0.61

<bos>

0.60

</strong>

0.59

Activations Density 1.942%

elements related to numerical data and measurements

No Comments

No Known Activations