INDEX

Explanations

terms related to permission and approval processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

DockStyle

-0.66

oneofs

-0.56

EndContext

-0.53

клопе

-0.52

UrlResolution

-0.52

 believer

-0.46

 typelib

-0.46

modelBuilder

-0.45

 gabbana

-0.45

ectady

-0.44

POSITIVE LOGITS

 approval

0.75

 consent

0.68

approval

0.63

 Approval

0.60

consent

0.59

 Consent

0.58

Approval

0.56

 authorisation

0.55

 Autorisations

0.55

 permission

0.52

Activations Density 0.520%

terms related to permission and approval processes

No Comments

No Known Activations