INDEX

Explanations

terms related to security and the act of securing something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

CompilerServices

-0.73

 CreateTagHelper

-0.70

 actionTypes

-0.67

labus

-0.65

MessageTagHelper

-0.65

pointers

-0.64

iecie

-0.63

ilanth

-0.63

plotlib

-0.63

 newArray

-0.62

POSITIVE LOGITS

 secure

2.86

Secure

2.70

 Secure

2.67

 secured

2.65

secure

2.62

 Secured

2.40

secured

2.30

 secures

2.29

Secured

2.28

 securing

2.25

Activations Density 0.066%

terms related to security and the act of securing something

No Comments

No Known Activations