INDEX

Explanations

references to rows and configurations in a mathematical context

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

EDEFAULT

-0.43

balleur

-0.43

 Brief

-0.39

HasAnnotation

-0.39

BRIEF

-0.38

 BRIEF

-0.36

Rptr

-0.35

LocalizedString

-0.35

TemporalType

-0.35

ⓘ

-0.35

POSITIVE LOGITS

BagLayout

0.66

 rows

0.59

 Füßen

0.56

 Rows

0.55

 Männern

0.54

sizeCache

0.54

 numberOfRows

0.54

ffindor

0.53

setVerticalGroup

0.50

usermodel

0.50

Activations Density 0.032%

references to rows and configurations in a mathematical context

No Comments

No Known Activations