INDEX

Explanations

expressions related to quantification and specifications

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

évaluateur

-0.64

Демографія

-0.52

Personensuche

-0.52

migrationBuilder

-0.50

 Gebä

-0.49

PostExecute

-0.49

 Vordergrund

-0.47

 intptr

-0.47

 insuffisamment

-0.46

ConstraintMaker

-0.46

POSITIVE LOGITS

 among

0.47

 amongst

0.38

 parmi

0.37

 AMONG

0.36

下列

0.35

among

0.34

 /\.(

0.33

onAttach

0.32

JKLM

0.32

 either

0.31

Activations Density 0.564%

expressions related to quantification and specifications

No Comments

No Known Activations