INDEX

Explanations

patterns of gene-related abbreviations and scientific nomenclature

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

 kaka

-0.75

gdx

-0.73

 initComponents

-0.71

pyplot

-0.69

 Massa

-0.67

 impres

-0.67

 cref

-0.66

Koa

-0.65

Massa

-0.65

 corrid

-0.64

POSITIVE LOGITS

1.13

 uncin

0.92

 Urqu

0.91

Ull

0.90

 Ulysses

0.87

uve

0.87

 Upton

0.86

 ungu

0.86

UU

0.85

 női

0.85

Activations Density 0.297%

patterns of gene-related abbreviations and scientific nomenclature

No Comments

No Known Activations