INDEX

Explanations

terms related to processes and outcomes in biological research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 leçon

-0.58

 charité

-0.55

 ſche

-0.55

 boisson

-0.54

 editados

-0.49

 innovate

-0.49

 législation

-0.48

AndEndTag

-0.47

 laſt

-0.47

 beginnetje

-0.47

POSITIVE LOGITS

 creation

1.58

 introduction

1.33

 establishment

1.31

 formation

1.30

 removal

1.28

creation

1.28

 completion

1.20

use

1.19

 adoption

1.16

 issuance

1.15

Activations Density 1.899%

terms related to processes and outcomes in biological research

No Comments

No Known Activations