INDEX

Explanations

text related to statistical performance metrics and model evaluation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

TagHelpers

-0.58

Portály

-0.58

estacks

-0.56

RTEX

-0.55

 intptr

-0.54

ⓧ

-0.52

脚注の使い方

-0.50

 uintptr

-0.50

 שוליים

-0.50

InputModule

-0.49

POSITIVE LOGITS

 accuracy

1.42

 precision

1.21

 Accuracy

1.21

 Precision

1.08

accuracy

1.07

Precision

1.06

Accuracy

1.06

precision

1.05

 ACCUR

1.00

 PRECISION

0.92

Activations Density 1.318%

text related to statistical performance metrics and model evaluation

No Comments

No Known Activations