INDEX

Explanations

terms related to quantitative measurements and evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

TintMode

-0.84

 متعلقه

-0.80

 themſelves

-0.76

 itſelf

-0.76

FormTagHelper

-0.74

 myſelf

-0.73

 raiſ

-0.70

 betweenstory

-0.69

ThroughAttribute

-0.69

 reaſon

-0.68

POSITIVE LOGITS

PositiveButton

0.48

elif

0.42

 BoxDecoration

0.39

ROSS

0.39

keyup

0.39

viewWillAppear

0.38

κτηρισ

0.38

 Gesam

0.37

 cucchia

0.37

Activations Density 1.149%

terms related to quantitative measurements and evaluations

No Comments

No Known Activations