INDEX

Explanations

scientific terms related to gene expression and annotation processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 Sport

-0.44

Sport

-0.38

 Oral

-0.36

 sport

-0.36

sport

-0.33

 Agent

-0.32

MMC

-0.32

 Plant

-0.31

 tasted

-0.31

 oral

-0.31

POSITIVE LOGITS

 Winaray

0.67

 indígen

0.66

 increí

0.66

 estadounid

0.66

 Bioinformatics

0.65

 genomics

0.63

 Italijani

0.62

majánló

0.61

 incrí

0.61

 ddelwed

0.61

Activations Density 2.767%

scientific terms related to gene expression and annotation processes

No Comments

No Known Activations