INDEX

Explanations

terms related to protection and safeguarding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.41.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

PhysRev

-0.49

 correction

-0.44

 lancar

-0.43

Correction

-0.41

 poveznice

-0.40

 corrections

-0.39

AutoresizingMask

-0.39

 Correction

-0.38

dreamstime

-0.38

 useSelector

-0.37

POSITIVE LOGITS

 against

0.90

against

0.74

Against

0.74

 Against

0.71

 AGAINST

0.62

 contre

0.57

 מפ

0.57

 vulnerable

0.56

 valuables

0.56

 yourself

0.54

Activations Density 0.328%

terms related to protection and safeguarding

No Comments

No Known Activations