INDEX

Explanations

references to legal proceedings and medical reports involving a specific individual

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

"La" followed by another word

np_acts-logits-general · gemini-2.0-flash

La followed by letters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

TextWatcher

-0.48

lien

-0.47

WaitGroup

-0.46

Referencies

-0.45

 withRouter

-0.45

UnusedPrivate

-0.44

lì

-0.44

IBOutlet

-0.44

lí

-0.43

Lien

-0.43

POSITIVE LOGITS

La

3.13

La

3.03

la

2.98

la

2.43

LA

2.33

LA

2.21

 Ла

2.04

Ла

1.89

 ла

1.73

Laf

1.67

Activations Density 0.402%

references to legal proceedings and medical reports involving a specific individual

"La" followed by another word

La followed by letters

No Comments

No Known Activations