INDEX

Explanations

phrases related to algorithm performance and evaluations in computational methods

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

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

ⓧ

-0.77

onomía

-0.61

homonymie

-0.57

 contextLoads

-0.56

########.

-0.56

Tembelea

-0.55

bufio

-0.55

typeorm

-0.53

 FormControl

-0.53

 MediatR

-0.52

POSITIVE LOGITS

 results

0.90

 experiments

0.85

 performance

0.78

Experiments

0.78

 tested

0.78

 simulations

0.76

experiments

0.75

 Results

0.75

 Experiments

0.75

 tests

0.72

Activations Density 1.555%

phrases related to algorithm performance and evaluations in computational methods

No Comments

No Known Activations