INDEX

Explanations

references to steps and processes in various methods or studies

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

preceding stages or steps in a process

np_acts-logits-general · gemini-2.0-flash

step or stage

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 resourceCulture

-0.68

 समीक्षाएं

-0.62

urlencoded

-0.61

 Мексичка

-0.59

 snippetHide

-0.58

 joaat

-0.56

Personensuche

-0.54

찮

-0.53

 disambiguazione

-0.53

Spot

-0.51

POSITIVE LOGITS

 step

2.80

 stage

2.71

 phase

2.39

step

2.32

stage

2.19

 stages

2.11

 Step

2.06

 steps

2.05

Step

2.02

 Stage

2.01

Activations Density 0.641%

references to steps and processes in various methods or studies

preceding stages or steps in a process

step or stage

No Comments

No Known Activations