INDEX

Explanations

references to measurements or evaluations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 propOrder

-0.60

 UnityEngine

-0.51

्यालय

-0.48

updateUI

-0.44

 availability

-0.44

-0.43

let

-0.42

└──

-0.42

imdi

-0.41

 rağmen

-0.41

POSITIVE LOGITS

}$_

0.72

strix

0.71

σθαι

0.70

انيف

0.67

extAlignment

0.66

performs

0.65

IsMutable

0.63

 miei

0.62

 sonno

0.62

 ExecuteAsync

0.62

Activations Density 0.506%

references to measurements or evaluations

No Comments

No Known Activations