INDEX

Explanations

instances of mathematical equivalences and formal assessments

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

SourceChecksum

-0.84

invokeLater

-0.68

Portale

-0.67

igshid

-0.66

 NSCoder

-0.65

็จ

-0.65

complexContent

-0.64

\{\\

-0.63

'],'

-0.61

</caption>

-0.61

POSITIVE LOGITS

equiv

0.72

 smoke

0.62

za

0.55

RESERVED

0.54

ef

0.53

sha

0.52

 CommonModule

0.51

 live

0.51

 Verbre

0.49

 smoked

0.48

Activations Density 0.136%

instances of mathematical equivalences and formal assessments

No Comments

No Known Activations