INDEX

Explanations

metrics related to evaluation scales and scoring systems

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

 VIAF

-0.58

kezés

-0.52

Pranala

-0.47

 проблему

-0.47

 Sizes

-0.47

ામ

-0.47

 CanadaChoose

-0.47

Timetable

-0.46

contentLoaded

-0.46

出版年

-0.46

POSITIVE LOGITS

 score

3.05

score

2.59

 Score

2.47

 scores

2.40

Score

2.29

 scoring

2.04

 scored

2.04

 SCORE

1.97

 Scores

1.96

SCORE

1.95

Activations Density 0.348%

metrics related to evaluation scales and scoring systems

No Comments

No Known Activations