INDEX

Explanations

references to DNA and its related processes

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

nict

-0.60

 monasterio

-0.59

kel

-0.56

providedIn

-0.55

 year

-0.54

 Mostly

-0.53

ustu

-0.53

 useSelector

-0.53

ManagedBean

-0.52

 Fros

-0.52

POSITIVE LOGITS

DNA

3.15

DNA

2.96

dna

2.32

dna

2.02

ADN

1.73

ADN

1.59

DN

1.39

RNA

1.24

 nucleic

1.23

RNA

1.17

Activations Density 0.155%

references to DNA and its related processes

No Comments

No Known Activations