INDEX

Explanations

programming-related comments and annotations

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

Follows a parameter or asterisk

np_acts-logits-general · gemini-2.0-flash

documentation tags

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

دانشنامهٔ

-0.67

ſelves

-0.60

 itſelf

-0.59

:✨

-0.57

$_(

-0.57

webElementXpaths

-0.54

 ſche

-0.54

MessageOf

-0.53

 queſta

-0.51

 iſt

-0.50

POSITIVE LOGITS

 defaultstate

0.68

Ligações

0.45

icherung

0.42

NameInMap

0.37

 Chwiliwch

0.36

 espoir

0.36

อะไร

0.35

 елның

0.35

Rol

0.34

Sklici

0.34

Activations Density 0.035%

programming-related comments and annotations

Follows a parameter or asterisk

documentation tags

No Comments

No Known Activations