INDEX

Explanations

references to personal preferences and customization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

tonsoft

-0.47

ltä

-0.45

WithTag

-0.45

 bonitas

-0.43

TabIndex

-0.43

 Normdatei

-0.42

Condol

-0.41

 ricas

-0.41

 وتسجيلات

-0.41

Mnemonic

-0.40

POSITIVE LOGITS

 needs

1.34

 circumstances

1.28

needs

1.22

 requirements

1.14

 circonstances

1.14

 nature

1.11

 Needs

1.10

 situation

1.10

 circumstance

1.05

requirements

1.05

Activations Density 0.497%

references to personal preferences and customization

No Comments

No Known Activations