INDEX

Explanations

names and family relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 صوتيه

-0.69

 RSSSF

-0.67

 seventies

-0.65

 müßte

-0.64

 läßt

-0.62

 USSR

-0.61

Dorothy

-0.60

المشاركات

-0.60

 Helga

-0.59

 Doreen

-0.59

POSITIVE LOGITS

 vPvB

0.65

élien

0.63

 Instagram

0.63

 Dylan

0.61

 barista

0.58

pektor

0.58

haal

0.56

 Hannah

0.56

 Jared

0.55

Hannah

0.55

Activations Density 0.384%

names and family relationships

No Comments

No Known Activations