INDEX

Explanations

technical terms and symbols related to data structures

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

Tokens followed by numbers

np_acts-logits-general · gemini-2.0-flash

mathematical expressions and numbers

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

 Fourth

-1.17

Fourth

-1.15

 fourth

-1.14

-1.04

④

-1.02

fourth

-1.01

 FOURTH

-0.95

 quartet

-0.91

IV

-0.87

第四

-0.86

POSITIVE LOGITS

 cheese

0.61

fifths

0.58

cheese

0.58

 Cheese

0.56

 grandmother

0.55

Cheese

0.54

 Friday

0.53

Friday

0.52

 yPos

0.51

pite

0.50

Activations Density 0.769%

technical terms and symbols related to data structures

Tokens followed by numbers

mathematical expressions and numbers

No Comments

No Known Activations