INDEX

Explanations

terms related to reproduction and reproducibility in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 Eisenberg

-0.81

Leopold

-0.74

-0.70

 Wolfe

-0.70

neurial

-0.70

 Rauch

-0.67

protoimpl

-0.65

arnia

-0.63

oara

-0.61

itectura

-0.61

POSITIVE LOGITS

 reproduces

1.31

 reproducing

1.25

 reproduce

1.25

 reprodu

1.25

 Reprodu

1.25

reprodu

1.20

 reproduced

1.18

 Reproduction

1.17

 reproduction

1.16

Reproduction

1.06

Activations Density 0.669%

terms related to reproduction and reproducibility in various contexts

No Comments

No Known Activations