INDEX

Explanations

reference to scores or ratings in various assessments

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

Something being scored, scaled, or indexed

np_acts-logits-general · gemini-2.0-flash

scores and ratings

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 esimer

-0.44

 CanadaChoose

-0.43

 disponibilités

-0.43

DeleteBehavior

-0.43

ConstraintMaker

-0.42

SessionFactory

-0.41

 سنت

-0.41

OGND

-0.41

verwijspagina

-0.40

akit

-0.40

POSITIVE LOGITS

 score

2.96

 scores

2.55

 Score

2.52

 scoring

2.50

score

2.49

 scored

2.40

 rating

2.35

Score

2.35

 Scoring

2.21

 Scores

2.20

Activations Density 0.744%

reference to scores or ratings in various assessments

Something being scored, scaled, or indexed

scores and ratings

No Comments

No Known Activations