INDEX

Explanations

personal pronouns

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

 autorytatywna

-0.65

ConstraintMaker

-0.63

 pinulongan

-0.54

 فريبيس

-0.50

 оригіналу

-0.48

 confusión

-0.46

.*")]

-0.46

:✨

-0.45

RTEE

-0.44

sendLogPayload

-0.44

POSITIVE LOGITS

PMS

0.47

PMS

0.45

arcoma

0.44

CPM

0.44

HAP

0.42

REA

0.42

fxml

0.42

CMP

0.41

NgModule

0.41

 Infants

0.41

Activations Density 0.000%

personal pronouns

No Comments

No Known Activations