INDEX

Explanations

references to servers and server-related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

➡

-0.81

 InputDecoration

-0.80

 Alcott

-0.71

hhhhhhhh

-0.68

 IDEA

-0.65

TryParse

-0.65

gleich

-0.65

 taches

-0.65

InteropServices

-0.64

 awakeFromNib

-0.64

POSITIVE LOGITS

 servers

1.49

 SERVER

1.41

 Server

1.39

 Servers

1.37

 server

1.34

SERVER

1.31

Server

1.29

 smtplib

1.25

server

1.25

Servers

1.20

Activations Density 0.084%

references to servers and server-related terminology

No Comments

No Known Activations