INDEX

Explanations

terms and phrases related to logging in and authentication processes

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

xrLabel

-0.45

tagHelperRunner

-0.44

featureID

-0.42

+#+#

-0.42

migrationBuilder

-0.41

windowFixed

-0.40

AutoScaleMode

-0.40

 deserto

-0.40

 TextAppearance

-0.39

findpost

-0.39

POSITIVE LOGITS

 login

0.68

LOGIN

0.63

 LoginForm

0.62

 logged

0.62

logout

0.62

 loggedIn

0.59

 Logged

0.59

 logout

0.59

login

0.58

 getLogin

0.57

Activations Density 0.139%

terms and phrases related to logging in and authentication processes

No Comments

No Known Activations