INDEX

Explanations

discounted offers or suggestions related to products or services

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

Non-English words or characters

np_acts-logits-general · gemini-2.0-flash

languages, data, and technical terms

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

ScopeManager

-0.58

рядок

-0.57

lägen

-0.55

 ہے۔

-0.55

ibol

-0.53

();)

-0.52

ड़ा

-0.51

jähriger

-0.50

ίδι

-0.50

`"

-0.49

POSITIVE LOGITS

 NSCoder

0.82

 صوتيه

0.69

 TextAppearance

0.65

 invokingState

0.63

 autorytatywna

0.63

ConstraintMaker

0.63

تقاوى

0.61

__(/*!

0.61

StoryboardSegue

0.59

:✨

0.58

Activations Density 0.013%

discounted offers or suggestions related to products or services

Non-English words or characters

languages, data, and technical terms

No Comments

No Known Activations