INDEX

Explanations

quantitative expressions and evaluations related to observations or results in studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

SourceChecksum

-0.45

 Cooperative

-0.40

 allowed

-0.37

gorm

-0.36

 Experiment

-0.35

 Retard

-0.35

orte

-0.35

 Allowed

-0.34

 gerecht

-0.34

 introduced

-0.34

POSITIVE LOGITS

帖最后由

0.63

 препратки

0.63

Personensuche

0.60

NameInMap

0.59

 Савезне

0.55

 ErrIntOverflow

0.54

Microkernel

0.54

ModelSerializer

0.53

 AssemblyTitle

0.52

Personendaten

0.50

Activations Density 1.035%

quantitative expressions and evaluations related to observations or results in studies

No Comments

No Known Activations