INDEX

Explanations

HTML tags and formatting elements

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

HTML list items

np_acts-logits-general · gemini-2.0-flash

list items

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

unknownFields

-0.68

#![

-0.64

Vidite

-0.57

èdia

-0.56

 pinulongan

-0.53

 demografica

-0.53

 AspNetCore

-0.52

 Chwiliwch

-0.52

stateProvider

-0.51

NavController

-0.51

POSITIVE LOGITS

 NgModule

0.65

 rowspan

0.63

 frigate

0.61

 obel

0.61

 présidentielle

0.60

 chiffon

0.58

 audiobook

0.56

balho

0.55

 windmill

0.54

droj

0.54

Activations Density 0.010%

HTML tags and formatting elements

HTML list items

list items

No Comments

No Known Activations