INDEX

Explanations

references to security features and gated properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

出版年

-0.75

 للمعارف

-0.60

notated

-0.59

-0.58

Gizmos

-0.55

IBOutlet

-0.52

 يتيمه

-0.51

 erop

-0.50

PerformLayout

-0.49

Ideally

-0.49

POSITIVE LOGITS

 gate

0.74

 entrance

0.72

 entry

0.71

 access

0.68

 gates

0.66

 Entrance

0.66

 entrada

0.65

 Entry

0.65

 password

0.65

 toegang

0.65

Activations Density 0.291%

references to security features and gated properties

No Comments

No Known Activations