INDEX

Explanations

references to a specific individual or character named Azcona

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

 Kandy

-0.77

Hoi

-0.75

 Ressource

-0.72

EMP

-0.69

Hoi

-0.67

 keskus

-0.67

anat

-0.66

 Amiens

-0.65

 Appleton

-0.64

 Schme

-0.64

POSITIVE LOGITS

Az

2.41

Az

2.14

az

2.05

az

2.04

AZ

1.65

AZ

1.64

azi

1.06

Azo

1.04

Azur

0.96

 Azad

0.93

Activations Density 0.100%

references to a specific individual or character named Azcona

No Comments

No Known Activations