INDEX

Explanations

references to the name "Bo" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 للاسماء

-0.77

InvalidProtocol

-0.76

CWE

-0.74

RectangleBorder

-0.74

 AspNetCore

-0.73

ghalaya

-0.68

nsyn

-0.64

 Cune

-0.61

aggia

-0.60

 Barcelone

-0.60

POSITIVE LOGITS

Bo

3.60

Bo

3.42

bo

2.89

bo

2.74

BO

2.23

BO

2.10

Boe

1.57

 Бо

1.44

ボ

1.38

 Boone

1.29

Activations Density 0.019%

references to the name "Bo" in various contexts

No Comments

No Known Activations