INDEX

Explanations

references to fame, whether it be highlighting famous individuals, notable works, or infamous events

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

Erreferentziak

-0.57

luster

-0.52

 asmen

-0.52

AutoScaleMode

-0.52

rtl

-0.52

IContainer

-0.51

 Esch

-0.50

RemoveField

-0.49

BuildContext

-0.49

Дереккөздер

-0.49

POSITIVE LOGITS

 famous

2.81

famous

2.61

 Famous

2.52

Famous

2.42

 famosa

2.01

 famoso

2.00

 berühmten

1.81

 famosas

1.77

 famosos

1.75

 célèbre

1.71

Activations Density 0.108%

references to fame, whether it be highlighting famous individuals, notable works, or infamous events

No Comments

No Known Activations