INDEX

Explanations

phrases related to improvement and enhancement in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

PathVariable

-0.75

Koz

-0.64

 HasFactory

-0.61

ers

-0.59

yl

-0.57

yaxis

-0.57

zk

-0.55

 Yank

-0.55

 cadeia

-0.55

ne

-0.55

POSITIVE LOGITS

 Improvements

1.39

esserung

1.33

 improvement

1.32

 Improvement

1.30

Improvements

1.29

 improvements

1.29

 Improves

1.28

improve

1.28

 IMPRO

1.27

 improves

1.27

Activations Density 0.093%

phrases related to improvement and enhancement in various contexts

No Comments

No Known Activations