INDEX

Explanations

occurrences of the word "gen" and its variations, related to genomic concepts and terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90

Prompts (Dashboard)

24,576 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

Diweddarwch

-0.46

 Gegenteil

-0.41

 administr

-0.39

 strconv

-0.37

 Euchar

-0.37

 Política

-0.37

 Municip

-0.37

 strpos

-0.36

Rod

-0.35

 Mand

-0.35

POSITIVE LOGITS

Gen

3.11

Gen

3.09

gen

2.97

gen

2.72

GEN

2.22

GEN

1.96

 Gens

1.30

 genotype

1.20

 Generation

1.20

 gens

1.19

Activations Density 0.180%

occurrences of the word "gen" and its variations, related to genomic concepts and terms

No Comments

No Known Activations