INDEX

Explanations

expressions of personal opinions and reactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

RenderAtEndOf

-0.76

יוחד

-0.63

Portail

-0.62

AndEndTag

-0.58



-0.58

DockStyle

-0.56

WebServlet

-0.56

KEYCODE

-0.56

 ولد

-0.56

PyExc

-0.55

POSITIVE LOGITS

///</

0.57

 think

0.54

 guess

0.54

 nahilalakip

0.54

 Cientí

0.53

fjspx

0.52

 wasn

0.52

 shouldn

0.51

 feels

0.51

isn

0.50

Activations Density 0.314%

expressions of personal opinions and reactions

No Comments

No Known Activations