INDEX

Explanations

references to individuals in a group or team context

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

team members or staff

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

:+:

-0.63

 BoxFit

-0.57

########.

-0.56

 disambiguazione

-0.53

 MatDialog

-0.53

fjspx

-0.52

libft

-0.52

hoeddwyd

-0.51

DockStyle

-0.50

 AssemblyTitle

-0.49

POSITIVE LOGITS

 coworker

0.53

 colleague

0.52

Person

0.51

 person

0.51

 collaborator

0.50

Employee

0.49

Location

0.48

person

0.48

stander

0.48

 friend

0.47

Activations Density 0.013%

references to individuals in a group or team context

team members or staff

No Comments

No Known Activations