INDEX

Explanations

references to logical connections and relationships, particularly involving "or" and "nor."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

-0.56

 sveta

-0.50

 fibrillation

-0.50

-0.46

-0.44

）

-0.44

 Humanos

-0.44

 maisha

-0.43

 diferite

-0.43

 brut

-0.42

POSITIVE LOGITS

Personensuche

0.98

 חיצוניים

0.88

IUrlHelper

0.85

ніципалі

0.78

principalTable

0.77

 nahilalakip

0.76

Tazama

0.76

GeoNames

0.74

 تانيه

0.73

 فريبيس

0.73

Activations Density 1.018%

references to logical connections and relationships, particularly involving "or" and "nor."

No Comments

No Known Activations