INDEX

Explanations

references to coding or programming structures related to data parsing and object decoding

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

艋

-0.60

 SwitchCompat

-0.59

󠁬

-0.55

writeFieldEnd

-0.54

AsUp

-0.54

Personensuche

-0.54

 ویکی‌پدیای

-0.53

󠁣

-0.53

GraphicsUnit

-0.53

titleMargin

-0.53

POSITIVE LOGITS

 judiciales

0.40

 horno

0.37

 myös

0.37

Bureau

0.35

äfts

0.34

 duros

0.34

Wot

0.34

 nemlig

0.33

tvr

0.33

 sauve

0.33

Activations Density 0.015%

references to coding or programming structures related to data parsing and object decoding

No Known Activations