INDEX

Explanations

numerical values and mathematical expressions

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

Numbers enclosed in brackets

np_acts-logits-general · gemini-2.0-flash

prime factors

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

脚注の使い方

-0.54

AddTagHelper

-0.53

GetMapping

-0.51

 McGuire

-0.47

 surla

-0.45

 atsi

-0.44

 rien

-0.43

InSection

-0.43

Side

-0.43

 Side

-0.42

POSITIVE LOGITS

 وتسجيلات

0.69

 nahilalakip

0.66

ंदीखरीदारी

0.64

 phim

0.58

 CreateTagHelper

0.58

 LUMP

0.57

 ListTile

0.57

فاده

0.56

UserScript

0.55

 gawas

0.55

Activations Density 0.725%

numerical values and mathematical expressions

Numbers enclosed in brackets

prime factors

No Comments

No Known Activations