INDEX

Explanations

mathematical expressions and notations associated with probability and statistical models

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/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.15.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

CrossRef

-0.82

 незавершена

-0.73

leurs

-0.70

subsubsection

-0.62

afficheront

-0.62

 LUMP

-0.61

Portály

-0.61

 Johnston

-0.60

atasaray

-0.60

Diwedd

-0.60

POSITIVE LOGITS

 esquerdo

0.82

 oorsp

0.69

MessageTagHelper

0.67

 kandang

0.65

</h2>

0.62

кто

0.62

0.61

 Henne

0.61

 canst

0.61

 disposto

0.61

Activations Density 0.378%

mathematical expressions and notations associated with probability and statistical models

No Comments

No Known Activations