INDEX

Explanations

specific keywords and labels related to research or data analysis

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

 الرياضيه

-0.77

 históricas

-0.63

 saisir

-0.58

eraard

-0.53

 &___

-0.52

 froh

-0.52

ganggu

-0.52

 mélanger

-0.51

 amoureux

-0.51

msgTypes

-0.50

POSITIVE LOGITS

SourceChecksum

0.75

DebuggerNonUser

0.75

UnusedPrivate

0.63

withstanding

0.63

"},

0.61

 архивлан

0.57

enumi

0.57

المشاركات

0.56

()];

0.56

"=>

0.56

Activations Density 0.092%

specific keywords and labels related to research or data analysis

No Comments

No Known Activations