INDEX

Explanations

references to legal concepts and terms related to damages and reputation

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

 المعيارى

-0.70

 للمعارف

-0.67

ViewFeatures

-0.65

 AssemblyCulture

-0.64

 ""],

-0.62

 مشين

-0.60

CloseOperation

-0.60

 Infórmanos

-0.59

 &___

-0.58

Izvori

-0.57

POSITIVE LOGITS

 wyłącznie

0.38

 kişilik

0.37

 sintético

0.36

 reducido

0.36

 paard

0.35

 bezpośred

0.35

 raad

0.35

 toekomst

0.35

 mieć

0.35

 perdido

0.34

Activations Density 1.130%

references to legal concepts and terms related to damages and reputation

No Comments

No Known Activations