INDEX

Explanations

key details related to conditions, evidence, and examples 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

 ब्रेकडाउन

-0.84

IsMutable

-0.83

 HasFactory

-0.66

WebServlet

-0.65

 autorytatywna

-0.63

الدراسه

-0.59

DockStyle

-0.59

IsContent

-0.59

Personendaten

-0.58

 Normdatei

-0.57

POSITIVE LOGITS

delwed

0.36

就知道

0.34

unmodifiable

0.29

§

0.27

السكان

0.27

pere

0.27

ionate

0.26

mio

0.26

Cay

0.26

bonnet

0.26

Activations Density 0.865%

key details related to conditions, evidence, and examples in various contexts

No Comments

No Known Activations