INDEX

Explanations

references to personal financial information and individual legal claims

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

"Personal" or related words

np_acts-logits-general · gemini-2.0-flash

personal and individual capacities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

AddTagHelper

-0.61

ACIAS

-0.54

ǔ

-0.54

adaptiveStyles

-0.50

otesi

-0.49

 horns

-0.49

queryInterface

-0.49

pital

-0.49

 demurrer

-0.47

ênes

-0.47

POSITIVE LOGITS

 personal

3.10

personal

2.71

 personally

2.70

Personal

2.59

 Personal

2.54

 PERSONAL

2.39

 personales

2.30

 pribadi

2.26

PERSONAL

2.23

 persönliche

2.21

Activations Density 0.467%

references to personal financial information and individual legal claims

"Personal" or related words

personal and individual capacities

No Comments

No Known Activations