INDEX

Explanations

terms related to groups of people, particularly in educational or organizational contexts

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

institutional roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

LabelTagHelper

-0.43

 urbanas

-0.42

بوابة

-0.41

addGap

-0.39

httphttps

-0.39

delwed

-0.38

SequentialGroup

-0.37

denver

-0.37

urban

-0.37

GraphicsUnit

-0.37

POSITIVE LOGITS

 staff

0.74

 employes

0.63

 employees

0.60

 staffers

0.60

staff

0.60

 Staff

0.57

Staff

0.56

STAFF

0.53

職員

0.51

 Employees

0.50

Activations Density 0.042%

terms related to groups of people, particularly in educational or organizational contexts

institutional roles

No Comments

No Known Activations