INDEX

Explanations

terms associated with interception and surveillance activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 trekken

-0.48

 peine

-0.46

gione

-0.44

 tarto

-0.44

коно

-0.42

 recommandée

-0.42

 tqdm

-0.41

 modelli

-0.40

SetBool

-0.40

 precisam

-0.40

POSITIVE LOGITS

 intercept

1.01

 intercepted

1.00

 eaves

0.96

 hack

0.89

 intercepts

0.88

 hijack

0.86

 overheard

0.82

AndEndTag

0.82

 interception

0.80

intercept

0.79

Activations Density 0.991%

terms associated with interception and surveillance activities

No Comments

No Known Activations