INDEX

Explanations

phrases that express uncertainty or questioning

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

AsyncResult

-0.50

roek

-0.45

colgante

-0.45

 UIAlert

-0.45

ToAction

-0.41

 smtplib

-0.41

migrationBuilder

-0.41

وصلات

-0.40

corazón

-0.40

RTLR

-0.40

POSITIVE LOGITS

到底

0.60

究竟

0.54

到底是

0.47

請問

0.46

 Autorisations

0.45

 Pamplona

0.44

Geplaatst

0.40

Hochspringen

0.40

awtextra

0.39

WireFormatLite

0.38

Activations Density 0.512%

phrases that express uncertainty or questioning

No Comments

No Known Activations