INDEX

Explanations

references to the letter "N" in various contexts and forms

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

starting with "N" followed by two letters

np_acts-logits-general · gemini-2.0-flash

words starting with N

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

InputTagHelper

-0.56

 above

-0.50

 change

-0.47

 complex

-0.47

fan

-0.46

complex

-0.44

 Check

-0.44

 changes

-0.43

 despite

-0.43

mpel

-0.43

POSITIVE LOGITS

 EconPapers

0.78

saraba

0.77

IntoConstraints

0.69

 crdi

0.68

 photolibrary

0.67

 NSCoder

0.64

HtmlAttribute

0.63

noinspection

0.62

ThroughAttribute

0.60

 ModelRenderer

0.60

Activations Density 0.180%

references to the letter "N" in various contexts and forms

starting with "N" followed by two letters

words starting with N

No Comments

No Known Activations