INDEX

Explanations

references to evidence or identification in a criminal context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

</strong>

-0.47

“

-0.46

</h2>

-0.44

↵

-0.42

-0.39

 further

-0.38

 some

-0.37

блица

-0.37

me

-0.37

POSITIVE LOGITS

 MainAxisSize

1.11

 للاسماء

1.10

AndEndTag

1.03

LookAnd

0.99

 وتسجيلات

0.94

 ModelExpression

0.93

PhysRev

0.93

Personendaten

0.92

 initComponents

0.92

Становништво

0.92

Activations Density 0.165%

references to evidence or identification in a criminal context

No Comments

No Known Activations