INDEX

Explanations

terms related to specific proteins and their functionalities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 Southgate

-0.81

fatt

-0.78

التالي

-0.77

 Saxe

-0.75

 toad

-0.72

 Middleton

-0.70

 pata

-0.70

 arrayList

-0.69

 pads

-0.68

 Australie

-0.68

POSITIVE LOGITS

 Shasta

1.03

']?>

0.86

 Burrow

0.83

 Burnett

0.82

BUR

0.81

Bur

0.81

 Gracie

0.81

kenstock

0.80

 Shapiro

0.80

 dysplasia

0.79

Activations Density 0.540%

terms related to specific proteins and their functionalities

No Comments

No Known Activations