INDEX

Explanations

themes related to crime and criminal activity

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

DrawerToggle

-0.42

tedra

-0.41

Discografia

-0.40

AccessorTable

-0.40

tæ

-0.39

 Paglinawan

-0.39

Xna

-0.38

yorum

-0.35

 ReactDOM

-0.35

enderror

-0.35

POSITIVE LOGITS

 robbery

0.72

 heist

0.65

 Robbery

0.61

 stolen

0.61

 burglar

0.59

 robberies

0.59

 Heist

0.57

 robbers

0.57

 burglary

0.55

 robbed

0.54

Activations Density 0.161%

themes related to crime and criminal activity

No Comments

No Known Activations