INDEX

Explanations

terms related to biological data analysis and medical conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 كومونز

-0.73

OptionsMenu

-0.66

 OnInit

-0.66

HasForeignKey

-0.65

-0.59

herself

-0.57

/*

-0.57

fraid

-0.56

стреча

-0.56

ResumeLayout

-0.56

POSITIVE LOGITS

 alike

0.59

Jîn

0.57

 domestiques

0.49

 niitä

0.47

ьаж

0.45

 MessageBoxIcon

0.45

ferous

0.44

bunden

0.43

 buruk

0.43

andte

0.42

Activations Density 0.581%

terms related to biological data analysis and medical conditions

No Comments

No Known Activations