INDEX

Explanations

names of prominent individuals and figures in various contexts

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

+:+

-0.43

Nab

-0.42

 parti

-0.42

rug

-0.39

 grower

-0.39

SATA

-0.38

grow

-0.38

Bri

-0.38

Bry

-0.37

bag

-0.35

POSITIVE LOGITS

 dezelve

0.64

 ویکی‌پدی

0.57

 geweest

0.56

 macetas

0.56

 määrä

0.55

 Italijani

0.54

 traseira

0.54

 informacija

0.53

 mitään

0.53

 almohada

0.52

Activations Density 0.602%

names of prominent individuals and figures in various contexts

No Comments

No Known Activations