INDEX

Explanations

technical terminology related to programming and data manipulation

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

 nakalista

-0.91

EndGlobalSection

-0.68

rrggbb

-0.61

IconModule

-0.52

 /\.(

-0.51

 PropertyChanged

-0.51

 defStyleAttr

-0.51

yakarta

-0.50

DebuggerNonUser

-0.50

PerformLayout

-0.50

POSITIVE LOGITS

zzino

0.56

 wanted

0.54

ьаж

0.52

 result

0.51

})*/

0.51

avyzd

0.50

"]=

0.49

سط

0.49

 memori

0.49

icher

0.48

Activations Density 0.161%

technical terminology related to programming and data manipulation

No Comments

No Known Activations