INDEX

Explanations

terms related to cybersecurity and hacking activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 InputDecoration

-0.78

̚

-0.76

zbęd

-0.75

̓

-0.74

peł

-0.72

","","

-0.72

avadoc

-0.69

intenance

-0.68

allee

-0.68

IMPLEMENTATION

-0.67

POSITIVE LOGITS

 cyber

1.82

 Cyber

1.80

Cyber

1.60

 ciber

1.38

cyber

1.34

Cy

1.30

cy

1.26

 cybersecurity

1.14

Cy

1.13

cy

1.02

Activations Density 0.095%

terms related to cybersecurity and hacking activities

No Comments

No Known Activations