INDEX

Explanations

scientific terms related to theoretical models and analyses

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

EndContext

-0.47

 PERSONAL

-0.46

Personensuche

-0.42

 personality

-0.41

GeneratedValue

-0.41

VIAF

-0.41

lesias

-0.41

SharedCtor

-0.41

 HttpNotFound

-0.41

 Personality

-0.40

POSITIVE LOGITS

 simplify

0.48

omock

0.46

MLLoader

0.45

 derive

0.45

 simplified

0.44

 derivation

0.42

 membahas

0.41

simplified

0.41

вості

0.41

/*

0.40

Activations Density 2.314%

scientific terms related to theoretical models and analyses

No Comments

No Known Activations