INDEX

Explanations

names of people and associated actions or roles

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

reporting speech or attribution

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 autorytatywna

-0.57

HideFlags

-0.57

WriteTagHelper

-0.52

mobileqq

-0.52

ंदीखरीदारी

-0.48

Cyfeiriadau

-0.47

новништво

-0.47

uxxxx

-0.46

 الحره

-0.46

Tembelea

-0.45

POSITIVE LOGITS

 said

0.51

setVerticalGroup

0.45

 explained

0.42

UnusedPrivate

0.42

 meinte

0.39

 explains

0.39

 spiega

0.38

said

0.37

 indisponible

0.36

 says

0.35

Activations Density 0.008%

names of people and associated actions or roles

reporting speech or attribution

No Comments

No Known Activations