INDEX

Explanations

elements related to user identification and naming conventions

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

user names and nicknames

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

脚注の使い方

-0.63

pexpr

-0.54

 AssemblyTitle

-0.54

 CreateTagHelper

-0.53

Décès

-0.52

 HasFactory

-0.51

InSection

-0.51

 Мексичка

-0.50

 beſch

-0.49

édrale

-0.49

POSITIVE LOGITS

 username

1.10

username

0.94

 usernames

0.87

 Username

0.84

Username

0.82

 pseudonym

0.81

 name

0.76

UserName

0.74

 nickname

0.73

 alias

0.73

Activations Density 0.027%

elements related to user identification and naming conventions

user names and nicknames

No Comments

No Known Activations