INDEX

Explanations

mathematical terminology and symbols, particularly in equations and expressions

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

Mathematical or programming notation

np_acts-logits-general · gemini-2.0-flash

width =

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 doubtnut

-1.35

 itſelf

-1.32

 myſelf

-1.29

 ſeveral

-1.25

ſelf

-1.20

 Diſ

-1.18

 Reſ

-1.13

 Hift

-1.13

 فريبيس

-1.12

 Majefty

-1.11

POSITIVE LOGITS

0.90

0.85

0.82

0.80

0.79

0.78

0.77

0.76

Activations Density 3.454%

mathematical terminology and symbols, particularly in equations and expressions

Mathematical or programming notation

width =

No Comments

No Known Activations