INDEX

Explanations

phrases related to algorithms and their performance metrics

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

comparison or changes

np_acts-logits-general · gemini-2.0-flash

comparison and change

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

setVerticalGroup

-0.78

#+#

-0.76

AutoScale

-0.68

abestanden

-0.62

 propOrder

-0.61

principalTable

-0.61

 useStyles

-0.61

 createState

-0.58

 PLWABN

-0.58

ècie

-0.58

POSITIVE LOGITS

 compared

3.71

compared

3.11

 Compared

2.79

Compared

2.67

 compare

2.54

 dibandingkan

2.41

 comparison

2.35

 compares

2.29

 rispetto

2.23

 dibanding

2.13

Activations Density 1.374%

phrases related to algorithms and their performance metrics

comparison or changes

comparison and change

No Comments

No Known Activations