INDEX

Explanations

names of organizations, places, and significant entities

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

Location or organization names

np_acts-logits-general · gemini-2.0-flash

organization offices and sites

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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



-0.94

 noDo

-0.81

 שוליים

-0.78

tagHelperRunner

-0.74

rrggbb

-0.72

帖最后由

-0.71

MemoryWarning

-0.70

Diweddarwch

-0.70

 CreateTagHelper

-0.69

 MainAxisSize

-0.69

POSITIVE LOGITS

 headquarters

0.70

 offices

0.62

 office

0.54

şim

0.52

 booth

0.51

HQ

0.51

 Headquarters

0.50

 sede

0.48

 desk

0.48

 storage

0.47

Activations Density 0.494%

names of organizations, places, and significant entities

Location or organization names

organization offices and sites

No Comments

No Known Activations