INDEX

Explanations

terms related to connections and relationships between different entities or factors

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

orado

-0.49

openzeppelin

-0.45

utnik

-0.45

っしゃ

-0.44

ElementException

-0.43

 cách

-0.42

 Heff

-0.42

america

-0.40

 eventual

-0.40

AndEndTag

-0.40

POSITIVE LOGITS

enumii

0.76

GEBURTSDATUM

0.75

 متعلقه

0.73

GIVEREF

0.68

WriteTagHelper

0.67

enumi

0.67

JspWriter

0.66

 antara

0.66

Биография

0.65

contentLoaded

0.64

Activations Density 0.467%

terms related to connections and relationships between different entities or factors

No Comments

No Known Activations