INDEX

Explanations

references to routines or regular practices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 piatti

-0.62

 WAYS

-0.55

 الرخصة

-0.55

protobuf

-0.53

 maneras

-0.53

GraphicsUnit

-0.51

 ways

-0.49

 immédi

-0.48

 età

-0.48

 rayures

-0.48

POSITIVE LOGITS

 render

0.86

Received

0.81

 فريبيس

0.81

 Render

0.74

 routine

0.74

 Rendering

0.72

 rendering

0.71

}$

0.70

Receive

0.68

 renders

0.68

Activations Density 0.143%

references to routines or regular practices

No Comments

No Known Activations