INDEX

Explanations

keywords and references related to programming or software development concepts

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

"info" (followed by certain punctuation/suffixes)

np_acts-logits-general · gemini-2.0-flash

info and information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

Xaml

-0.49

TestTools

-0.47

 recurrent

-0.46

́ng

-0.45

 Scribd

-0.44

 Portuguesa

-0.44

setContentView

-0.43

 Leidenschaft

-0.43

AddTagHelper

-0.43

ismet

-0.43

POSITIVE LOGITS

 info

2.67

info

2.52

 Info

2.47

Info

2.45

 information

2.27

 INFO

2.26

INFO

2.19

 infos

2.10

information

2.08

 getInfo

2.06

Activations Density 0.072%

keywords and references related to programming or software development concepts

"info" (followed by certain punctuation/suffixes)

info and information

No Comments

No Known Activations