INDEX

Explanations

terms related to sensitivity in various contexts, particularly in relation to biological and electronic systems

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

lot

-0.68

 divertimento

-0.62

 Crowley

-0.61

 posta

-0.60

Tow

-0.59

lot

-0.59

 Fact

-0.59

KEEP

-0.58

หม

-0.58

кто

-0.58

POSITIVE LOGITS

 Sensitive

1.55

 sensitive

1.55

Sensitive

1.47

 sensitivity

1.43

 sensi

1.42

 vulnerability

1.36

 sensitivities

1.35

sensitive

1.29

 Sensitivity

1.27

Sensi

1.23

Activations Density 0.196%

terms related to sensitivity in various contexts, particularly in relation to biological and electronic systems

No Comments

No Known Activations