INDEX

Explanations

mentions of user-related identifiers, specifically the term "username"

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

ValueStyle

-1.03

 Seeder

-0.93

دانشنامهٔ

-0.93

awaiter

-0.83

Moq

-0.82

setof

-0.81

apollo

-0.80

 Lyra

-0.79

*}$

-0.79

Tikang

-0.79

POSITIVE LOGITS

 username

0.77

 whoſe

0.73

Wur

0.73

username

0.71

mistic

0.71

 Theſe

0.71

Username

0.68

 Wür

0.67

 setUsername

0.64

 Username

0.64

Activations Density 0.117%

mentions of user-related identifiers, specifically the term "username"

No Comments

No Known Activations