INDEX

Explanations

terms indicating permission or enabling actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

projectName

-0.33

 архивлан

-0.33

CIS

-0.31

Rie

-0.31

StringCopy

-0.30

<strong>

-0.29

Démographie

-0.29

KommentareTeilen

-0.28

mad

-0.28

Rie

-0.28

POSITIVE LOGITS

 autorytatywna

0.81

ALLOW

0.69

allow

0.67

Allows

0.67

 Allows

0.66

 ALLOW

0.65

 Allow

0.65

 Italijanski

0.64

Allow

0.62

GTCX

0.62

Activations Density 0.154%

terms indicating permission or enabling actions

No Comments

No Known Activations