INDEX

Explanations

expressions of self-reflection or self-criticism

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

--]

-0.47

}\{

-0.47

ười

-0.46

uttavia

-0.46

 utafitiHapana

-0.46

wolle

-0.46

ciatore

-0.45

}{*}{

-0.45

tyimages

-0.44

 PyObject

-0.44

POSITIVE LOGITS

fjspx

0.58

AutoScale

0.57

 StatefulWidget

0.56

ArrowToggle

0.56

 TextInputType

0.55

ⓘ

0.55

 kaarangay

0.53

 protège

0.51

 grecque

0.51

asanjo

0.51

Activations Density 0.202%

expressions of self-reflection or self-criticism

No Comments

No Known Activations