INDEX

Explanations

instances of alerts and alert-related functionality in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

RegressionTest

-0.84

transQ

-0.80

istock

-0.80

)?;

-0.78

antMatchers

-0.77

GraphicsUnit

-0.77

consin

-0.76

opsida

-0.76

)');

-0.76

'));

-0.75

POSITIVE LOGITS

Alerts

1.07

 alerts

1.05

 Alerts

0.99

ALERT

0.96

 alert

0.92

alerts

0.92

 Alert

0.89

 ALERT

0.84

 Balt

0.83

 Ballard

0.82

Activations Density 0.163%

instances of alerts and alert-related functionality in code

No Comments

No Known Activations