INDEX

Explanations

references to presidents and related political figures

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

Following the word "President"

np_acts-logits-general · gemini-2.0-flash

President followed by leader's name

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 defaultstate

-0.97

 Roskov

-0.81

хьтан

-0.66

CloseOperation

-0.66

κτηρισ

-0.66

 مرئيه

-0.63

PyExc

-0.61

ỡng

-0.61

erráneo

-0.60

itude

-0.59

POSITIVE LOGITS

Elect

0.64

 elect

0.60

 Elect

0.58

tagHelper

0.53

Enllaços

0.50

ReusableCell

0.48

valget

0.48

 Obama

0.47

 Barack

0.46

 goutte

0.46

Activations Density 0.072%

references to presidents and related political figures

Following the word "President"

President followed by leader's name

No Comments

No Known Activations